INDEX

Explanations

information related to specific entities or topics

oai_token-act-pair · gpt-3.5-turbo

subjective pronouns and verb phrases indicating actions or states

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

emption

-0.75

cock

-0.72

itely

-0.65

endment

-0.64

icka

-0.63

gered

-0.63

oller

-0.62

-0.61

 messing

-0.60

 Compatibility

-0.59

POSITIVE LOGITS

 mammoth

0.68

 paved

0.63

bes

0.62

cli

0.62

 Palestin

0.59

 nevertheless

0.58

 nonetheless

0.58

 doomed

0.57

 fraught

0.57

ls

0.57

Activations Density 0.347%

information related to specific entities or topics

subjective pronouns and verb phrases indicating actions or states

No Comments

No Known Activations