INDEX

Explanations

text related to translations, attributions, and permissions

oai_token-act-pair · gpt-3.5-turbo

references to translations and attributions in text

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

ipeg

-0.79

kefeller

-0.65

ilyn

-0.62

 gobl

-0.61

artney

-0.61

 payday

-0.59

 Weston

-0.59

itol

-0.59

gered

-0.56

hester

-0.55

POSITIVE LOGITS

utf

0.69

 guiActiveUnfocused

0.67

UTF

0.67

Pattern

0.64

ragon

0.63

isms

0.63

 Deity

0.62

taboola

0.62

minus

0.62

 verbs

0.61

Activations Density 1.422%

text related to translations, attributions, and permissions

references to translations and attributions in text

No Comments

No Known Activations