INDEX

Explanations

phrases indicating repetition or continuity

oai_token-act-pair · gpt-3.5-turbo

references to the word "again."

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

rament

-0.86

izons

-0.80

ottage

-0.77

ocene

-0.73

kees

-0.72

eways

-0.69

oes

-0.69

adena

-0.69

avez

-0.68

vez

-0.65

POSITIVE LOGITS

 revolving

0.71

 reiterate

0.66

 echoing

0.66

adays

0.65

 assuming

0.65

 conclud

0.64

 Thomson

0.63

onse

0.63

here

0.62

entimes

0.62

Activations Density 0.025%

phrases indicating repetition or continuity

references to the word "again."

No Comments

No Known Activations