INDEX

Explanations

phrases indicating completion or continuing action

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

plementation

-0.62

poon

-0.61

ahime

-0.60

arium

-0.59

ync

-0.58

ictionary

-0.58

ister

-0.57

allion

-0.57

ucer

-0.56

alion

-0.56

POSITIVE LOGITS

way

0.87

 sudden

0.85

 rage

0.78

 same

0.78

 usual

0.76

things

0.75

 bells

0.74

 goddamn

0.70

licks

0.70

 while

0.69

Activations Density 0.042%

phrases indicating completion or continuing action

occurrences of the word "the."

No Comments

No Known Activations