INDEX

Explanations

words related to prominent names and entities, potentially with a focus on positions held or actions taken

oai_token-act-pair · gpt-3.5-turbo

the letter 'e' in various contexts

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

mallow

-0.78

iets

-0.76

 consolidation

-0.73

 sidx

-0.72

anova

-0.70

displayText

-0.69

*/(

-0.69

matic

-0.66

 carbohyd

-0.66

 BaseType

-0.65

POSITIVE LOGITS

lements

1.29

agle

1.01

gging

0.99

lev

0.98

gger

0.96

zza

0.94

ld

0.94

ep

0.94

ury

0.94

agles

0.93

Activations Density 0.034%

words related to prominent names and entities, potentially with a focus on positions held or actions taken

the letter 'e' in various contexts

No Comments

No Known Activations