INDEX

Explanations

mentions of the name "Ker" with varying degrees of activation

oai_token-act-pair · gpt-3.5-turbo

references to a specific individual named "Kerley."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

BOOK

-0.81

UME

-0.79

IBLE

-0.78

terday

-0.74

ãģį

-0.73

Uncommon

-0.73

ablishment

-0.73

EMENT

-0.72

 à¨

-0.70

ÙĲ

-0.70

POSITIVE LOGITS

rigan

1.17

sten

1.05

bil

0.98

mit

0.98

der

0.96

ston

0.90

©¶æ

0.88

lins

0.87

rod

0.87

ules

0.86

Activations Density 0.010%

mentions of the name "Ker" with varying degrees of activation

references to a specific individual named "Kerley."

No Comments

No Known Activations