INDEX

Explanations

phrases related to circumcision

oai_token-act-pair · gpt-3.5-turbo

references to circumcision and related terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hips

-0.91

wagen

-0.76

 Waterloo

-0.74

OHN

-0.73

WP

-0.72

 Beet

-0.72

 Archdemon

-0.66

 Petro

-0.66

iston

-0.65

 Gleaming

-0.65

POSITIVE LOGITS

scribed

1.16

 circum

1.10

cision

1.09

vention

1.01

cised

0.96

pei

0.90

scribe

0.87

cise

0.87

spect

0.78

thodox

0.75

Activations Density 0.013%

phrases related to circumcision

references to circumcision and related terms

No Comments

No Known Activations