INDEX

Explanations

references to proper nouns (names) related to the name "Dick"

oai_token-act-pair · gpt-3.5-turbo

references to individuals named "Dick" 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xual

-0.77

kees

-0.76

srf

-0.74

ccording

-0.69

yip

-0.66

 Carbuncle

-0.65

 adversity

-0.64

 waters

-0.64

 tradem

-0.64

 Aval

-0.64

POSITIVE LOGITS

enson

1.02

 Cheney

0.98

erson

0.93

ible

0.90

ie

0.85

inson

0.84

 Grayson

0.84

buster

0.83

inges

0.80

stein

0.80

Activations Density 0.014%

references to proper nouns (names) related to the name "Dick"

references to individuals named "Dick" in various contexts

No Comments

No Known Activations