INDEX

Explanations

words related to people's names, specifically the name "William" with a strong activation value

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "William."

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

yrinth

-0.86

rador

-0.78

ebook

-0.75

wrapper

-0.74

chio

-0.74

displayText

-0.73

asio

-0.71

ADRA

-0.71

ordinate

-0.70

hess

-0.70

POSITIVE LOGITS

son

0.92

\\\\\\\\

0.91

sburg

0.87

 Randolph

0.85

stown

0.85

 Faul

0.83

 Hague

0.83

 Wallace

0.80

ette

0.80

 William

0.80

Activations Density 0.017%

words related to people's names, specifically the name "William" with a strong activation value

mentions of the name "William."

No Comments

No Known Activations