INDEX

Explanations

words related to worn items or personal belongings

oai_token-act-pair · gpt-3.5-turbo

words related to negative physical effects or behaviors

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

 Kills

-0.79

GMT

-0.72

 Reborn

-0.72

 Participant

-0.66

 Solitaire

-0.66

MENTS

-0.65

 Daylight

-0.64

MENT

-0.64

:]

-0.64

 Abbey

-0.63

POSITIVE LOGITS

aring

0.88

asting

0.87

ipping

0.86

alog

0.86

orting

0.82

oldown

0.82

itored

0.81

istance

0.81

ivery

0.80

ility

0.80

Activations Density 0.113%

words related to worn items or personal belongings

words related to negative physical effects or behaviors

No Comments

No Known Activations