INDEX

Explanations

references to the word "stick" and its variations

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

出版年

-0.73

Personensuche

-0.60

bayes

-0.58

CMA

-0.57

zA

-0.57

 BorderRadius

-0.57

dafx

-0.57

 Faure

-0.55

bhan

-0.55

avir

-0.54

POSITIVE LOGITS

 stick

1.01

stick

0.96

 Stick

0.93

Stick

0.91

 STICK

0.89

 sticking

0.85

 sticks

0.81

 stuck

0.81

STICK

0.71

Stuck

0.68

Activations Density 0.006%

references to the word "stick" and its variations

No Comments

No Known Activations