INDEX

Explanations

objects involved in theft or criminal activities

oai_token-act-pair · gpt-3.5-turbo

nouns related to theft or items that are stolen

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Noise

-0.64

 valleys

-0.63

iets

-0.62

 advers

-0.62

 jurisdiction

-0.62

 academia

-0.59

 tenure

-0.59

 continuum

-0.58

 departments

-0.58

lishes

-0.58

POSITIVE LOGITS

 coupons

0.86

 stash

0.80

 souven

0.79

 belonging

0.78

 containing

0.77

 smuggled

0.77

 valued

0.77

nings

0.75

 contents

0.74

 replica

0.74

Activations Density 0.753%

objects involved in theft or criminal activities

nouns related to theft or items that are stolen

No Comments

No Known Activations