INDEX

Explanations

mentions of unidentified or unnamed entities

oai_token-act-pair · gpt-3.5-turbo

references to unnamed or unidentified subjects in reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

byss

-0.82

ometers

-0.77

nea

-0.76

arium

-0.75

agall

-0.74

ĸļ

-0.73

odium

-0.72

kept

-0.71

*=-

-0.70

=-=-=-=-=-=-=-=-

-0.69

POSITIVE LOGITS

 unnamed

0.99

 unspecified

0.87

 persons

0.82

 unidentified

0.80

 undisclosed

0.74

aneous

0.73

 quantity

0.72

 assailants

0.72

 sources

0.72

 narrator

0.69

Activations Density 0.051%

mentions of unidentified or unnamed entities

references to unnamed or unidentified subjects in reports

No Comments

No Known Activations