INDEX

Explanations

words related to a specific male group or category

oai_token-act-pair · gpt-3.5-turbo

references to male individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

VICE

-0.72

Dog

-0.71

BILL

-0.67

 kernels

-0.67

Pwr

-0.65

IVERS

-0.65

ENC

-0.64

EAR

-0.62

Ear

-0.62

INO

-0.61

POSITIVE LOGITS

opausal

1.12

gling

1.10

uscript

1.02

endez

0.95

volent

0.94

å£«

0.92

thren

0.92

hood

0.92

orah

0.90

istan

0.87

Activations Density 0.016%

words related to a specific male group or category

references to male individuals or groups

No Comments

No Known Activations