INDEX

Explanations

words related to illegal activities or violations

oai_token-act-pair · gpt-3.5-turbo

terms related to drug usage and its implications

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

 Shroud

-0.65

 neutron

-0.59

likely

-0.58

Ant

-0.58

 dist

-0.57

rising

-0.57

 latitude

-0.56

 totality

-0.56

 undert

-0.55

ext

-0.55

POSITIVE LOGITS

gging

3.60

gged

3.57

ggy

3.10

ggie

2.93

gger

2.29

ggies

2.24

gg

2.00

ggle

1.95

ggles

1.52

gs

1.42

Activations Density 0.020%

words related to illegal activities or violations

terms related to drug usage and its implications

No Comments

No Known Activations