INDEX

Explanations

phrases related to events or incidents happening in a specific location

oai_token-act-pair · gpt-3.5-turbo

introductory phrases or transitions

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

 Mate

-0.64

 Volunteer

-0.63

',

-0.59

 ILCS

-0.57

Bul

-0.57

'.

-0.56

éĹĺ

-0.56

 cutter

-0.55

Jur

-0.55

 VIDE

-0.54

POSITIVE LOGITS

Else

0.90

mosp

0.76

hesda

0.74

elf

0.72

alyst

0.71

Weak

0.70

:(

0.68

avascript

0.67

phabet

0.66

APS

0.65

Activations Density 0.156%

phrases related to events or incidents happening in a specific location

introductory phrases or transitions

No Comments

No Known Activations