INDEX

Explanations

function-related keywords that indicate actions or methods in code

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

Code, symbols, and non-English words

np_acts-logits-general · gemini-2.0-flash

programming identifiers and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.64

-0.58

-0.54

-0.52

-0.50

-0.48

-0.47

POSITIVE LOGITS

ContentAsync

1.06

 Monfieur

0.98

 linkovi

0.97

().

0.95

 ويكيپيديا

0.93

ByVersion

0.93

 estekak

0.92

 AssemblyTitle

0.90

()->

0.90

ChildScrollView

0.89

Activations Density 0.165%

function-related keywords that indicate actions or methods in code

Code, symbols, and non-English words

programming identifiers and technical terms

No Comments

No Known Activations