INDEX

Explanations

references to statistical distributions and their properties

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

Excerpt

-0.55

toe

-0.49

 incenti

-0.47

<tbody>

-0.47

 EconPapers

-0.46

↵↵

-0.45

>>;

-0.45

avras

-0.45

 Dooley

-0.45

 offset

-0.44

POSITIVE LOGITS

 distributions

1.66

 Distributed

1.55

 Distributions

1.55

 distribution

1.55

 DISTRIB

1.54

 distributed

1.53

 Distribute

1.52

 Distribution

1.50

Dist

1.49

 distribute

1.47

Activations Density 0.165%

references to statistical distributions and their properties

No Comments

No Known Activations