INDEX

Explanations

expressions related to scientific experiments

oai_token-act-pair · gpt-3.5-turbo

references to scientific experiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

nergy

-0.68

corruption

-0.66

othy

-0.65

MET

-0.64

partisan

-0.63

olulu

-0.63

flush

-0.62

lining

-0.62

miah

-0.60

games

-0.59

POSITIVE LOGITS

imental

1.08

 Experiment

1.07

 experiment

0.99

iments

0.99

iment

0.97

ually

0.88

eers

0.86

 experimented

0.84

uates

0.83

ally

0.83

Activations Density 0.009%

expressions related to scientific experiments

references to scientific experiments

No Comments

No Known Activations