INDEX

Explanations

instances where a particular person or political figure is mentioned

oai_token-act-pair · gpt-3.5-turbo

references to identity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

zzo

-0.88

avorite

-0.76

 âĨĳ

-0.71

Ħ¢

-0.71

 Lank

-0.69

azel

-0.69

scill

-0.68

 untreated

-0.68

¶ħ

-0.66

OTT

-0.66

POSITIVE LOGITS

ity

1.15

ident

1.12

ities

1.10

ifiers

1.05

ially

0.97

itarian

0.95

ifier

0.91

ifying

0.90

iary

0.89

ified

0.88

Activations Density 0.014%

instances where a particular person or political figure is mentioned

references to identity in various contexts

No Comments

No Known Activations