INDEX

Explanations

variations or different versions of something

oai_token-act-pair · gpt-3.5-turbo

terms related to variations or modifications of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ħĭ

-0.79

lins

-0.76

Ķ

-0.69

gement

-0.66

 skelet

-0.66

lehem

-0.64

friends

-0.64

\":

-0.63

¾

-0.63

İ

-0.62

POSITIVE LOGITS

 thereof

1.26

arily

0.98

 allele

0.84

 variants

0.79

iations

0.78

ary

0.78

 alle

0.76

 variations

0.73

aution

0.73

 spelling

0.73

Activations Density 0.066%

variations or different versions of something

terms related to variations or modifications of something

No Comments

No Known Activations