INDEX

Explanations

code-related elements focusing on cases and conditions within programming logic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ViewFeatures

-0.97

ValueStyle

-0.90

 AssemblyProduct

-0.90

Tembelea

-0.85

Efq

-0.78

LookAnd

-0.77

 InputDecoration

-0.77

 whereof

-0.76

StoryboardSegue

-0.75

/>";

-0.73

POSITIVE LOGITS

 flag

0.53

Flag

0.52

flag

0.52

 bool

0.51

0.50

wantErr

0.48

 boolean

0.48

 mode

0.45

or

0.45

 Flag

0.44

Activations Density 0.317%

code-related elements focusing on cases and conditions within programming logic

No Comments

No Known Activations