INDEX

Explanations

references to a specific person named Clarke at different significance levels

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Clarke."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

olulu

-0.86

xual

-0.82

llah

-0.81

awaru

-0.80

ricular

-0.79

ramid

-0.76

ebus

-0.74

lopp

-0.74

choes

-0.73

ebin

-0.72

POSITIVE LOGITS

 Clarke

1.13

 MacArthur

0.91

Clar

0.79

voy

0.69

worth

0.67

bott

0.67

isle

0.67

 Wheels

0.66

 Lawson

0.65

 Briggs

0.64

Activations Density 0.016%

references to a specific person named Clarke at different significance levels

mentions of the name "Clarke."

No Comments

No Known Activations