INDEX

Explanations

words related to references or mentioning

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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 whiff

-0.66

é¾įå

-0.62

urity

-0.61

miah

-0.59

Jed

-0.53

 underdog

-0.52

fall

-0.51

 impressions

-0.51

oppable

-0.50

 Marketplace

-0.49

POSITIVE LOGITS

entious

1.03

rers

0.98

to

0.87

 thereto

0.83

rer

0.83

to

0.73

rals

0.73

itionally

0.72

geon

0.69

ãĥĥ

0.68

Activations Density 0.026%

words related to references or mentioning

instances of the word "refer" and its variations

No Comments

No Known Activations