INDEX

Explanations

phrases related to prevention or inhibiting actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "prevent."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ammy

-0.87

eah

-0.68

edded

-0.68

enegger

-0.66

MON

-0.63

inging

-0.62

geist

-0.62

swick

-0.62

Word

-0.61

elt

-0.60

POSITIVE LOGITS

ative

1.04

 regress

0.83

 detection

0.79

ively

0.78

 duplicate

0.78

 accidental

0.73

 duplication

0.73

 pregnancies

0.73

ministic

0.73

 reprodu

0.71

Activations Density 0.034%

phrases related to prevention or inhibiting actions

instances of the word "prevent."

No Comments

No Known Activations