INDEX

Explanations

references to sources and their credibility in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

:✨

-0.62

 betweenstory

-0.50

ⓧ

-0.41

Autoritní

-0.40

VERTIS

-0.39

imetsu

-0.39

offerta

-0.39

 plow

-0.39

offrir

-0.39

nextDouble

-0.39

POSITIVE LOGITS

 ujednoznacz

0.57

 informants

0.56

 sources

0.52

sources

0.50

fromnode

0.49

tangentMode

0.49

UserScript

0.48

 fontes

0.47

 AssemblyCulture

0.47

Източници

0.46

Activations Density 0.008%

references to sources and their credibility in the text

No Comments

No Known Activations