INDEX

Explanations

names of people and places

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to people, places, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ĪĴ

-0.72

heid

-0.69

milo

-0.68

Downloadha

-0.66

ĨĴ

-0.65

FORMATION

-0.64

urtles

-0.59

ichita

-0.58

«ĺ

-0.58

 Unloaded

-0.58

POSITIVE LOGITS

 coffers

0.77

 psyche

0.76

's

0.67

 lately

0.62

 corners

0.56

verse

0.55

 territory

0.54

 aback

0.54

Mania

0.54

goers

0.53

Activations Density 0.839%

names of people and places

proper nouns related to people, places, and organizations

No Comments

No Known Activations