INDEX

Explanations

references to specific fields or topics of research in academic literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 typelib

-0.52

 román

-0.51

 quedado

-0.51

 memu

-0.51

культур

-0.49

 prends

-0.48

hå

-0.48

 proie

-0.47

$__

-0.47

 Muster

-0.47

POSITIVE LOGITS

 Thema

0.72

 endblock

0.72

antMatchers

0.66

EnableWeb

0.66

endsection

0.65

 transfieras

0.64

Portale

0.64

AutoScaleMode

0.64

SaveChanges

0.61

getColumnIndex

0.61

Activations Density 0.575%

references to specific fields or topics of research in academic literature

No Comments

No Known Activations