INDEX

Explanations

phrases indicating conditionality or dependence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tø

-0.55

 Regret

-0.53

 pribadi

-0.53

<h5>

-0.52

<strong>

-0.52

<em>

-0.52

-0.50

丛

-0.50

tim

-0.50

POSITIVE LOGITS

 depending

1.28

depending

1.19

 Depends

1.10

 depends

1.01

 Depending

0.95

Depending

0.93

depends

0.91

 dependiendo

0.90

 dependent

0.89

 unknownFields

0.87

Activations Density 0.166%

phrases indicating conditionality or dependence

No Comments

No Known Activations