INDEX

Explanations

instances of technical or programming jargon and specific code-related terms

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

Characters or symbols in code or math

np_acts-logits-general · gemini-2.0-flash

string ` ` }

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

الدراسه

-0.79

$_"

-0.68

 ་་

-0.65

theless

-0.65

 تضيفلها

-0.64

URLException

-0.61

 GenerationType

-0.60

AutoresizingMask

-0.60

SaveChangesAsync

-0.59

POSITIVE LOGITS

<eos>

0.78

↵↵

0.74

↵

0.74

IUrlHelper

0.73

NameInMap

0.72

Autoritní

0.71

();

0.64

LookAnd

0.64

WebElementEntity

0.62

Activations Density 0.650%

instances of technical or programming jargon and specific code-related terms

Characters or symbols in code or math

string ` ` }

No Comments

No Known Activations