INDEX

Explanations

words related to people's names

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific name or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

print

-0.63

 Sequ

-0.63

 entangled

-0.62

ERC

-0.62

EED

-0.62

reme

-0.61

NTS

-0.59

ulet

-0.58

Rated

-0.58

 Catalyst

-0.56

POSITIVE LOGITS

tered

1.08

mand

1.06

iflower

0.96

ters

0.94

vey

0.91

angelo

0.90

brook

0.88

ibrary

0.88

ms

0.86

iday

0.86

Activations Density 0.019%

words related to people's names

mentions of a specific name or entity

No Comments

No Known Activations