INDEX

Explanations

phrases indicating a sense of absoluteness or completeness

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate completeness or totality

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

pu

-0.68

 Reincarn

-0.63

 Patriarch

-0.56

Klu

-0.55

eer

-0.55

 Koen

-0.55

tru

-0.53

uph

-0.53

 entire

-0.53

 Chancellor

-0.53

POSITIVE LOGITS

ocating

0.93

 times

0.84

ogene

0.79

times

0.77

ones

0.75

 levels

0.73

 else

0.72

 except

0.69

TPP

0.69

 costs

0.69

Activations Density 0.032%

phrases indicating a sense of absoluteness or completeness

phrases that indicate completeness or totality

No Comments

No Known Activations