INDEX

Explanations

terms related to computing and programming, particularly references to "pc" (program counter) and "simulation" contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Great

-0.52

The

-0.51

cuta

-0.51

<h2>

-0.50

tí

-0.49

maila

-0.48

$('.

-0.47

стоя

-0.47

‘

-0.46

the

-0.46

POSITIVE LOGITS

pcs

0.94

Dell

0.89

 DELL

0.83

BeginInit

0.83

DELL

0.82

UnsafeEnabled

0.81

 Dell

0.80

oredCriteria

0.79

Хьажоргаш

0.78

pc

0.77

Activations Density 0.157%

terms related to computing and programming, particularly references to "pc" (program counter) and "simulation" contexts

No Comments

No Known Activations