INDEX

Explanations

strings or code snippets containing the word "From"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "from."

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

ratulations

-0.89

aired

-0.81

airs

-0.81

idav

-0.80

sylv

-0.75

irm

-0.75

mun

-0.74

isode

-0.72

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.71

important

-0.70

POSITIVE LOGITS

 afar

1.31

 whence

1.23

 scratch

1.21

 thence

1.03

 inception

0.91

 abroad

0.86

Uni

0.82

 infancy

0.79

 anywhere

0.79

 within

0.78

Activations Density 0.153%

strings or code snippets containing the word "From"

occurrences of the word "from."

No Comments

No Known Activations