INDEX

Explanations

words related to a decrease or reduction in something

oai_token-act-pair · gpt-3.5-turbo

references to decreasing values or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

nox

-0.74

haps

-0.74

Orig

-0.68

iasco

-0.66

Äĩ

-0.65

 Carnage

-0.64

ebook

-0.64

fiction

-0.64

istry

-0.63

wald

-0.63

POSITIVE LOGITS

 lower

3.40

lower

2.67

Lower

2.46

 Lower

2.38

 higher

2.27

 upper

2.12

higher

1.95

 lowest

1.87

Higher

1.85

 lowered

1.82

Activations Density 0.014%

words related to a decrease or reduction in something

references to decreasing values or quantities

No Comments

No Known Activations