INDEX

Explanations

specific programming and data structure terminology

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

expandindo

-0.59

AutoScaleMode

-0.58

Tikang

-0.57

Abitanti

-0.56

 informée

-0.56

Бахар

-0.54

 censiti

-0.53

الحياه

-0.51

 Audiodateien

-0.51

omitempty

-0.49

POSITIVE LOGITS

 foul

0.40

 وتسجيلات

0.38

ohu

0.38

umbres

0.38

ysql

0.38

 vile

0.37

…

0.36

…

0.36

 frost

0.35

 segni

0.35

Activations Density 0.087%

specific programming and data structure terminology

No Comments

No Known Activations