INDEX

Explanations

phrases related to organizations or groups

oai_token-act-pair · gpt-3.5-turbo

references to structured organizations or collective entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ystem

-0.88

ynthesis

-0.75

uggest

-0.73

hops

-0.66

omething

-0.65

Ô

-0.61

 Flavoring

-0.61

poons

-0.61

&&

-0.60

++

-0.59

POSITIVE LOGITS

 itself

1.34

's

1.28

wide

0.94

ultimate

0.92

ÃŃs

0.86

iest

0.84

liest

0.84

acious

0.81

 motto

0.79

 homepage

0.78

Activations Density 0.362%

phrases related to organizations or groups

references to structured organizations or collective entities

No Comments

No Known Activations