INDEX

Explanations

mentions of the word "shot"

oai_token-act-pair · gpt-3.5-turbo

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

herty

-0.77

éĸ

-0.69

 streng

-0.66

ebook

-0.65

Prin

-0.64

algia

-0.63

Case

-0.63

baum

-0.62

ŃĶ

-0.62

abeth

-0.61

POSITIVE LOGITS

gun

1.14

calling

1.09

guns

1.03

chens

0.90

 fired

0.84

call

0.84

nikov

0.82

shot

0.81

finder

0.78

tery

0.77

Activations Density 0.037%

mentions of the word "shot"

No Comments

No Known Activations