INDEX

Explanations

content related to ratings or evaluations of entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 незавершена

-0.81

protoimpl

-0.79

DockStyle

-0.77

новниш

-0.76

OGND

-0.73

windowFixed

-0.70

ScopeManager

-0.70

\{\\

-0.69

Искәрмәләр

-0.68

 linkovi

-0.68

POSITIVE LOGITS

ioutil

0.54

 stie

0.52

ーン

0.52

 legais

0.52

 Sachin

0.50

 Adobe

0.50

 affaire

0.49

 materiál

0.49

ính

0.49

 vectorielle

0.48

Activations Density 0.282%

content related to ratings or evaluations of entities

No Comments

No Known Activations