INDEX

Explanations

proper nouns and names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and titles

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abase

-0.90

hemy

-0.67

batch

-0.65

afety

-0.64

Äĩ

-0.63

uyomi

-0.63

irlf

-0.60

iasco

-0.59

imov

-0.57

tal

-0.56

POSITIVE LOGITS

 unlocked

0.55

zig

0.55

 Aden

0.51

 Manuel

0.51

 Webster

0.49

Zhu

0.49

 Lambert

0.49

zu

0.49

ora

0.49

opping

0.49

Activations Density 0.259%

proper nouns and names

proper nouns, specifically names and titles

No Comments

No Known Activations