INDEX

Explanations

specific terms and entities related to technical and scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 تانيه

-0.70

 يتيمه

-0.63

 Générale

-0.56

̍t

-0.53

expandindo

-0.52

 Audiodateien

-0.52

RenderAtEndOf

-0.52

ngdoc

-0.51

 recommandée

-0.50

labus

-0.49

POSITIVE LOGITS

+#+#

0.58

 hooked

0.58

yled

0.56

rad

0.55

rad

0.55

 Meksiku

0.54

Pi

0.53

ERT

0.53

COLN

0.52

InputBorder

0.52

Activations Density 2.928%

specific terms and entities related to technical and scientific contexts

No Comments

No Known Activations