INDEX

Explanations

references to media outlets or interviews

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

OGND

-0.61

fjspx

-0.59

 Lightboxes

-0.56

SourceChecksum

-0.53

ContentAsync

-0.50

 незавершена

-0.50

 Италијани

-0.48

 CreateTagHelper

-0.48

 autorytatywna

-0.47

 виправивши

-0.46

POSITIVE LOGITS

GHIJKLM

0.39

pencil

0.35

 gond

0.34

wapV

0.32

 Rocca

0.32

Dış

0.31

solving

0.31

Rozm

0.31

 inex

0.31

Slo

0.31

Activations Density 0.010%

references to media outlets or interviews

No Comments

No Known Activations