INDEX

Explanations

references to named entities, particularly those with 'NB' as a prefix followed by a number

oai_token-act-pair · gpt-3.5-turbo

mentions of the abbreviation "NB" that indicate various organizations or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

æ©

-0.91

ttle

-0.78

TYPE

-0.76

fare

-0.76

 Ãľ

-0.73

tails

-0.70

eve

-0.68

«ĺ

-0.65

worms

-0.65

venge

-0.63

POSITIVE LOGITS

NB

0.93

wik

0.89

ionics

0.88

emonic

0.85

ionic

0.78

eworthy

0.78

nb

0.75

NB

0.73

etheless

0.71

iotics

0.70

Activations Density 0.016%

references to named entities, particularly those with 'NB' as a prefix followed by a number

mentions of the abbreviation "NB" that indicate various organizations or contexts

No Comments

No Known Activations