INDEX

Explanations

nouns related to diseases or health issues

oai_token-act-pair · gpt-3.5-turbo

terms related to diseases or medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

etheless

-0.81

dies

-0.80

icals

-0.79

nesday

-0.78

istry

-0.75

asca

-0.72

anyl

-0.71

ding

-0.70

ishing

-0.70

ishop

-0.68

POSITIVE LOGITS

ppe

0.90

Ã±o

0.84

 versa

0.81

mble

0.81

lda

0.77

 Amend

0.76

eq

0.76

FontSize

0.74

olate

0.73

ller

0.71

Activations Density 0.089%

nouns related to diseases or health issues

terms related to diseases or medical conditions

No Comments

No Known Activations