INDEX

Explanations

references to political figures or activities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, especially names and titles of individuals

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lihood

-0.83

CONCLUS

-0.76

/>

-0.72

RESULTS

-0.72

thumbnails

-0.70

vg

-0.69

 Shutterstock

-0.69

MU

-0.67

 Leilan

-0.66

ilial

-0.66

POSITIVE LOGITS

reetings

0.73

 baseman

0.70

 whisky

0.65

hester

0.62

 frontman

0.60

achu

0.60

 dodged

0.60

 embattled

0.60

 footballer

0.58

 awoke

0.58

Activations Density 0.378%

references to political figures or activities

proper nouns, especially names and titles of individuals

No Comments

No Known Activations