INDEX

Explanations

comparisons or relationships between things, especially with negative connotations

oai_token-act-pair · gpt-3.5-turbo

critical commentary on societal issues and behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Showtime

-0.65

 arcs

-0.62

 captcha

-0.59

 Destination

-0.59

 sequence

-0.59

 fingerprints

-0.58

 Moments

-0.58

 roadmap

-0.58

 Aadhaar

-0.57

 Puzzles

-0.56

POSITIVE LOGITS

educated

1.06

trained

0.98

loving

0.96

minded

0.95

married

0.93

bred

0.93

arers

0.89

arians

0.89

acists

0.88

disabled

0.87

Activations Density 0.797%

comparisons or relationships between things, especially with negative connotations

critical commentary on societal issues and behaviors

No Comments

No Known Activations