INDEX

Explanations

words related to completion, progress, or instructions

oai_token-act-pair · gpt-3.5-turbo

punctuation and transitional phrases that emphasize significant points or changes in context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emaker

-0.76

lance

-0.69

minster

-0.66

mie

-0.66

Alias

-0.65

builder

-0.64

bir

-0.63

nik

-0.62

EMBER

-0.60

les

-0.60

POSITIVE LOGITS

 Flavoring

0.75

 Including

0.74

 including

0.73

including

0.71

 namely

0.70

txt

0.69

 Specifically

0.68

 Eventually

0.65

 Rohing

0.62

 please

0.62

Activations Density 1.016%

words related to completion, progress, or instructions

punctuation and transitional phrases that emphasize significant points or changes in context

No Comments

No Known Activations