INDEX

Explanations

names or proper nouns of people or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names associated with individuals or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etheless

-0.70

enegger

-0.67

 compr

-0.66

});

-0.66

ailability

-0.63

 accomp

-0.61

 cleaners

-0.60

tenance

-0.59

 respectively

-0.59

 constitu

-0.58

POSITIVE LOGITS

Zer

0.74

 Blog

0.70

imon

0.68

DD

0.67

obi

0.67

 Geek

0.67

zeb

0.66

ileaks

0.65

Stream

0.64

STAR

0.63

Activations Density 0.556%

names or proper nouns of people or entities

proper nouns and names associated with individuals or entities

No Comments

No Known Activations