INDEX

Explanations

words related to physical acts of biting

oai_token-act-pair · gpt-3.5-turbo

instances of the word "bite" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ourced

-0.79

å§«

-0.73

 Aerospace

-0.71

ources

-0.69

 Mathemat

-0.69

AMP

-0.66

 Pione

-0.66

UTION

-0.66

 Principal

-0.63

 Minister

-0.62

POSITIVE LOGITS

 bite

1.16

bite

1.12

 bitten

1.05

 Bite

0.97

terness

0.91

 bites

0.89

paste

0.86

vine

0.85

cliffe

0.81

hook

0.79

Activations Density 0.013%

words related to physical acts of biting

instances of the word "bite" and its variations

No Comments

No Known Activations