INDEX

Explanations

programming-related keywords and terms, particularly related to data structures or classes in code

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

qrstuvwxyz

-0.88

RegressionTest

-0.72

tonode

-0.71

principalColumn

-0.64

batore

-0.63

енча

-0.63

webElementXpaths

-0.61

/*---

-0.59

textAppearance

-0.59

ronpa

-0.58

POSITIVE LOGITS

 static

0.75

();)

0.65

 تضيفلها

0.64

 Vikipedi

0.63

reinterpret

0.61

static

0.55

 lateinit

0.55

 Static

0.54

expandindo

0.53

پیوند

0.53

Activations Density 0.010%

programming-related keywords and terms, particularly related to data structures or classes in code

No Comments

No Known Activations