INDEX

Explanations

names of people or titles in military or political contexts

oai_token-act-pair · gpt-3.5-turbo

proper nouns and titles related to individuals and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

CONCLUS

-0.77

RESULTS

-0.70

cells

-0.70

irs

-0.68

MU

-0.64

-0.63

Desktop

-0.62

grave

-0.62

groups

-0.61

POSITIVE LOGITS

 Rodham

0.80

 Richard

0.72

dinand

0.70

 Salvador

0.69

 Bryant

0.69

imir

0.69

 Christopher

0.68

 William

0.68

 Fernandez

0.68

 Edward

0.68

Activations Density 0.200%

names of people or titles in military or political contexts

proper nouns and titles related to individuals and their roles

No Comments

No Known Activations