INDEX

Explanations

names of individuals, organizations, and locations

oai_token-act-pair · gpt-3.5-turbo

names and titles related to individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

uers

-0.65

hip

-0.59

>>>>

-0.59

------------------------

-0.57

ADVERTISEMENT

-0.57

ornia

-0.56

ystem

-0.54

tml

-0.54

oward

-0.54

=(

-0.54

POSITIVE LOGITS

 itself

1.62

 herself

1.34

 themselves

1.32

 himself

1.24

 Himself

1.02

 ourselves

1.01

 yourself

0.90

 oneself

0.87

 yourselves

0.82

 myself

0.79

Activations Density 0.826%

names of individuals, organizations, and locations

names and titles related to individuals and organizations

No Comments

No Known Activations