INDEX

Explanations

proper nouns related to locations or names

oai_token-act-pair · gpt-3.5-turbo

names of people and places

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

 threaded

-0.71

anguage

-0.70

matically

-0.70

 inclined

-0.67

 deaf

-0.67

 filament

-0.65

 proximity

-0.64

 bombard

-0.63

âĸ¬âĸ¬

-0.63

WAYS

-0.62

POSITIVE LOGITS

ille

1.03

inelli

1.03

vy

0.96

iour

0.91

Sav

0.89

anas

0.89

elin

0.89

arro

0.87

arella

0.87

itri

0.87

Activations Density 0.013%

proper nouns related to locations or names

names of people and places

No Comments

No Known Activations