INDEX

Explanations

terms related to discussions or debates

oai_token-act-pair · gpt-3.5-turbo

terms related to discussions or debates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 dece

-0.76

 foll

-0.66

 bapt

-0.65

ren

-0.62

 Hebrew

-0.62

gar

-0.62

 mage

-0.61

est

-0.60

Gil

-0.59

dip

-0.59

POSITIVE LOGITS

ussed

3.94

ussions

3.26

ussion

2.82

uss

1.90

USS

1.49

ourage

1.28

ussian

1.20

retion

1.20

ourse

1.20

overed

1.15

Activations Density 0.027%

terms related to discussions or debates

terms related to discussions or debates

No Comments

No Known Activations