INDEX

Explanations

phrases that indicate past or repetitive information

oai_token-act-pair · gpt-3.5-turbo

the repetition of 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rament

-0.83

avez

-0.74

izons

-0.74

ottage

-0.72

kees

-0.71

 Jugg

-0.69

anooga

-0.68

ocene

-0.66

adena

-0.66

gio

-0.64

POSITIVE LOGITS

 conclud

0.72

 repeats

0.71

 Transcript

0.68

forth

0.68

 Thomson

0.66

 echoing

0.66

onse

0.66

nces

0.65

 invoking

0.64

entimes

0.62

Activations Density 0.022%

phrases that indicate past or repetitive information

the repetition of the word "Again."

No Comments

No Known Activations