INDEX

Explanations

mentions of actions related to theft or unauthorized taking

oai_token-act-pair · gpt-3.5-turbo

instances of the word "steal" and its variations

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

present

-0.74

band

-0.73

anamo

-0.71

pora

-0.70

olver

-0.70

night

-0.69

ichick

-0.67

bands

-0.65

rehens

-0.64

acerb

-0.63

POSITIVE LOGITS

 glances

0.87

weed

0.82

 stolen

0.77

ster

0.76

 stealing

0.73

 prey

0.71

sters

0.71

 away

0.70

ezvous

0.69

 steals

0.69

Activations Density 0.019%

mentions of actions related to theft or unauthorized taking

instances of the word "steal" and its variations

No Comments

No Known Activations