INDEX

Explanations

references to academic papers or proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 سكانية

-0.76

Hozzáférés

-0.66

RegistryLite

-0.64

JspWriter

-0.63

 للمعارف

-0.61

 ModelExpression

-0.61

 AssemblyProduct

-0.59

最快更新

-0.58

ContentAlignment

-0.57

 متعلقه

-0.57

POSITIVE LOGITS

 téléphonique

0.56

AppMethodBeat

0.48

 muualla

0.46

 datter

0.44

bericht

0.43

navigateTo

0.43

 partea

0.42

RegressionTest

0.42

 privileges

0.42

 doInBackground

0.41

Activations Density 0.080%

references to academic papers or proceedings

No Comments

No Known Activations