INDEX

Explanations

phrases related to social interactions where others are kind or supportive towards the subject

oai_token-act-pair · gpt-3.5-turbo

references to the pronoun "you."

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

ĨĴ

-0.69

 Commerce

-0.68

 Agriculture

-0.68

tein

-0.64

 Course

-0.64

 majority

-0.63

 Majority

-0.63

ħ

-0.61

 Politico

-0.61

WW

-0.61

POSITIVE LOGITS

're

1.18

tub

1.18

 guys

1.14

've

0.97

RS

0.93

hei

0.91

'll

0.89

selves

0.78

andering

0.75

kai

0.75

Activations Density 0.112%

phrases related to social interactions where others are kind or supportive towards the subject

references to the pronoun "you."

No Comments

No Known Activations