INDEX

Explanations

phrases related to technical information or data extraction

oai_token-act-pair · gpt-3.5-turbo

specific formatting and data indicators in raw text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dinand

-0.84

 undermin

-0.75

ritic

-0.73

 answ

-0.71

umenthal

-0.71

 photographers

-0.71

milo

-0.70

Downloadha

-0.69

soType

-0.69

osponsors

-0.68

POSITIVE LOGITS

Requirements

0.84

---

0.70

...]

0.69

 Paste

0.67

////

0.67

---

0.66

 =================================================================

0.66

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.65

Required

0.64

 ----------------------------------------------------------------

0.63

Activations Density 0.090%

phrases related to technical information or data extraction

specific formatting and data indicators in raw text

No Comments

No Known Activations