INDEX

Explanations

issues or events causing controversy or uproar

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significant public reactions or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

alan

-0.71

uthor

-0.67

alon

-0.67

acons

-0.67

enhagen

-0.66

aiden

-0.66

track

-0.65

essor

-0.65

orest

-0.65

anwhile

-0.64

POSITIVE LOGITS

 havoc

1.33

 disturbance

1.04

 headaches

1.00

 uproar

0.98

 mayhem

0.96

 stir

0.94

 damage

0.89

 unnecessary

0.89

 panic

0.89

 disruptions

0.88

Activations Density 0.189%

issues or events causing controversy or uproar

phrases indicating significant public reactions or consequences

No Comments

No Known Activations