INDEX

Explanations

names of locations or individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.76

 TIME

-0.70

 RELE

-0.60

 STATS

-0.58

 âĺ

-0.58

Reloaded

-0.58

 Nikki

-0.58

CLASSIFIED

-0.57

BIP

-0.57

Economic

-0.56

POSITIVE LOGITS

leck

0.79

auld

0.77

ynes

0.76

lems

0.75

ife

0.73

ahime

0.69

udos

0.69

inx

0.68

raine

0.67

rod

0.67

Activations Density 0.421%

names of locations or individuals

proper nouns, particularly names and places

No Comments

No Known Activations