INDEX

Explanations

references to prominent figures or people holding authoritative positions

oai_token-act-pair · gpt-3.5-turbo

references to political or organizational leaders

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

 ours

-0.65

Oo

-0.64

nder

-0.63

ighth

-0.63

gging

-0.62

 Moor

-0.60

 Mile

-0.60

gged

-0.59

INGTON

-0.59

OUT

-0.58

POSITIVE LOGITS

hip

0.99

hips

0.96

 negotiator

0.90

cius

0.88

paces

0.86

doms

0.84

esses

0.83

wcs

0.81

pins

0.80

 glim

0.78

Activations Density 0.022%

references to prominent figures or people holding authoritative positions

references to political or organizational leaders

No Comments

No Known Activations