INDEX

Explanations

references to utility functions or modules in code

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

gow

-0.55

󠁮

-0.54

SPJ

-0.54

Franck

-0.54

AndEndTag

-0.53

PageNumber

-0.51

LookAnd

-0.51

bign

-0.49

makeText

-0.49

posedge

-0.48

POSITIVE LOGITS

Util

1.30

 Util

1.27

 util

1.16

util

1.08

FileUtil

0.85

 utilitarian

0.83

UTIL

0.82

 UTIL

0.82

StringUtil

0.78

 utility

0.75

Activations Density 0.006%

references to utility functions or modules in code

No Comments

No Known Activations