INDEX

Explanations

phrases related to specific locations or establishments

oai_token-act-pair · gpt-3.5-turbo

references to specific brands, products, or notable public figures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pload

-0.69

abytes

-0.66

bnb

-0.63

htaking

-0.62

 glaciers

-0.60

ikuman

-0.60

hap

-0.59

uria

-0.58

drm

-0.58

achev

-0.58

POSITIVE LOGITS

Cly

0.60

QUIRE

0.56

itely

0.55

 Niet

0.55

 omission

0.54

 behalf

0.54

CTR

0.52

DIT

0.50

Sle

0.50

 Baird

0.50

Activations Density 1.336%

phrases related to specific locations or establishments

references to specific brands, products, or notable public figures

No Comments

No Known Activations