INDEX

Explanations

continuations in text

oai_token-act-pair · gpt-3.5-turbo

segments indicating ongoing content or articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

liest

-0.84

aster

-0.71

OH

-0.70

 honor

-0.70

 happiest

-0.69

uristic

-0.68

rams

-0.67

azer

-0.65

ogun

-0.65

unts

-0.64

POSITIVE LOGITS

 Continued

1.37

ĸļ

1.05

 Transcript

0.93

 Below

0.92

 Parenthood

0.80

...]

0.80

CLASSIFIED

0.76

sbm

0.74

 Continuing

0.73

 Flavoring

0.73

Activations Density 0.009%

continuations in text

segments indicating ongoing content or articles

No Comments

No Known Activations