INDEX

Explanations

phrases or words related to referencing or mentioning something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "refer" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 whiff

-0.64

cffff

-0.63

oppable

-0.63

urity

-0.62

avorite

-0.60

é¾įå

-0.59

opia

-0.59

airs

-0.59

cape

-0.57

iller

-0.56

POSITIVE LOGITS

irect

0.90

rers

0.88

entious

0.84

rences

0.81

 thereto

0.79

itatively

0.77

ãĥĥ

0.76

gently

0.73

ename

0.72

ciplinary

0.68

Activations Density 0.033%

phrases or words related to referencing or mentioning something

instances of the word "refer" and its variations

No Comments

No Known Activations