INDEX

Explanations

purposefully extreme or dangerous actions

oai_token-act-pair · gpt-3.5-turbo

the word "for" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sonian

-0.72

Ohio

-0.70

fleet

-0.69

subject

-0.66

olan

-0.65

KK

-0.65

mare

-0.63

hess

-0.62

hao

-0.62

uckland

-0.60

POSITIVE LOGITS

bidden

1.09

geries

1.08

 instance

1.08

 starters

1.08

 example

1.05

 purposes

0.97

gery

0.91

agers

0.89

aging

0.89

 eternity

0.89

Activations Density 0.262%

purposefully extreme or dangerous actions

the word "for" in various contexts

No Comments

No Known Activations