INDEX

Explanations

symbols and formatting structure in code or programming text

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

related to code testing

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.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

каза

-0.29

 music

-0.29

jet

-0.28

 getchar

-0.28

Box

-0.28

tag

-0.26

dep

-0.25

 firm

-0.25

 uovo

-0.25

 charging

-0.25

POSITIVE LOGITS

 виправивши

0.80

 betweenstory

0.73

 Vikipedi

0.69

yntaxException

0.68

Vidite

0.65

enumi

0.63

SpringRunner

0.62

 esternos

0.60

ConstraintMaker

0.60

 Expectations

0.59

Activations Density 0.000%

symbols and formatting structure in code or programming text

related to code testing

No Comments

No Known Activations