INDEX

Explanations

terms related to academic and professional titles and affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 ***!

-0.64

 defaultstate

-0.58

ống

-0.58

xase

-0.57

neux

-0.56

 ويكيميديا

-0.56

 referrerpolicy

-0.55

 sacrificio

-0.54

 onAnimation

-0.54

########.

-0.53

POSITIVE LOGITS

SerializedName

0.57

Associate

0.54

 Associate

0.51

ientí

0.51

 Emeritus

0.51

 Fellows

0.50

Honorary

0.50

Emer

0.50

 associate

0.50

ETIME

0.50

Activations Density 0.542%

terms related to academic and professional titles and affiliations

No Comments

No Known Activations

terms related to academic and professional titles and affiliations

No Comments

No Known Activations