INDEX

Explanations

mentions of additions or new elements being introduced

oai_token-act-pair · gpt-3.5-turbo

phrases related to new elements being incorporated or included

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rior

-0.76

zees

-0.67

zee

-0.65

rpm

-0.64

raz

-0.63

ms

-0.61

awar

-0.60

rage

-0.59

nc

-0.59

rolled

-0.56

POSITIVE LOGITS

endum

1.02

 thereto

0.91

xual

0.89

ition

0.79

 insult

0.77

verted

0.76

itives

0.73

 Flavoring

0.73

ement

0.71

xon

0.70

Activations Density 0.032%

mentions of additions or new elements being introduced

phrases related to new elements being incorporated or included

No Comments

No Known Activations