INDEX

Explanations

references to specific names, particularly the name "Gene"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Gene."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Demand

-0.80

ĺħ

-0.78

uckland

-0.77

yrim

-0.76

committee

-0.75

 Pradesh

-0.74

izoph

-0.73

etheless

-0.73

ulhu

-0.72

initialized

-0.70

POSITIVE LOGITS

alogy

1.40

alog

1.16

etics

0.99

Gene

0.90

etically

0.83

 Gene

0.80

etic

0.78

Lys

0.78

 Simmons

0.77

Kru

0.76

Activations Density 0.005%

references to specific names, particularly the name "Gene"

mentions of the name "Gene."

No Comments

No Known Activations