INDEX

Explanations

the name "Jerome"

oai_token-act-pair · gpt-3.5-turbo

references to specific names related to individuals and their actions or roles

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

tle

-1.08

gins

-1.02

nam

-0.99

icles

-0.98

terness

-0.96

lest

-0.95

icle

-0.93

nesses

-0.93

Interstitial

-0.90

ificial

-0.86

POSITIVE LOGITS

xual

0.96

 Morocco

0.83

 Scotia

0.83

anwhile

0.78

 reception

0.76

 Beau

0.74

 Bastard

0.73

 Royale

0.70

 Philippe

0.70

 Ples

0.69

Activations Density 0.044%

the name "Jerome"

references to specific names related to individuals and their actions or roles

No Comments

No Known Activations