INDEX

Explanations

terms related to the primary subject or central concept in a text

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the concept of focus or attention

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

Äį

-0.71

 paradise

-0.69

 +---

-0.65

 intest

-0.63

 decom

-0.63

azo

-0.62

 scraps

-0.62

oshenko

-0.62

 decaying

-0.62

cav

-0.61

POSITIVE LOGITS

ORTS

0.79

 Attention

0.76

akers

0.75

quickShipAvailable

0.67

orial

0.67

orically

0.66

 Lauder

0.66

ORGE

0.66

 specificity

0.65

 Beir

0.62

Activations Density 0.335%

terms related to the primary subject or central concept in a text

phrases that emphasize the concept of focus or attention

No Comments

No Known Activations