INDEX

Explanations

expressions of uncertainty or possibility

oai_token-act-pair · gpt-3.5-turbo

expressions of uncertainty or conditionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

asus

-0.78

isal

-0.72

llah

-0.70

aml

-0.70

cation

-0.69

etheless

-0.65

pora

-0.64

mania

-0.62

Leader

-0.62

bara

-0.62

POSITIVE LOGITS

 themselves

1.17

 selves

1.08

selves

0.85

 helmets

0.78

MpServer

0.78

 individually

0.77

 mouths

0.72

endez

0.69

 wills

0.69

 leases

0.69

Activations Density 0.940%

expressions of uncertainty or possibility

expressions of uncertainty or conditionality

No Comments

No Known Activations