INDEX

Explanations

the name "Arthur" with varying levels of activation

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the name "Arthur."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

href

-0.75

ongyang

-0.74

initialized

-0.73

Ĥ¬

-0.70

ple

-0.69

racted

-0.69

ramid

-0.68

ered

-0.68

resent

-0.67

arity

-0.66

POSITIVE LOGITS

 Ashe

1.09

 Arthur

0.96

 Pend

0.94

 Weasley

0.93

 Conan

0.86

itic

0.85

 Clarke

0.81

andise

0.73

 Guinness

0.72

ite

0.72

Activations Density 0.010%

the name "Arthur" with varying levels of activation

repeated mentions of the name "Arthur."

No Known Activations