INDEX

Explanations

references to physical aspects and parameters of objects, particularly in a technical or scientific context

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

technical or structured-text markers—capitalized headings, labels, parameters, warnings, and code-like identifiers in figure captions or documentation.

oai_token-act-pair · gpt-5 Triggered by @timna

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

IMPORTED

-0.56

 pstmt

-0.53

 EconPapers

-0.52

//

-0.52

WindowConstants

-0.51

WEBPACK

-0.51

îtra

-0.49

literals

-0.48

__':

-0.48

yargs

-0.47

POSITIVE LOGITS

UnusedPrivate

0.89

 nahilalakip

0.87

 '\\;'

0.83

 ModelExpression

0.71

IsMutable

0.67

])));

0.65

ropolitan

0.64

RVA

0.63

HtmlAttribute

0.61

AnchorStyles

0.60

Activations Density 0.201%

references to physical aspects and parameters of objects, particularly in a technical or scientific context

technical or structured-text markers—capitalized headings, labels, parameters, warnings, and code-like identifiers in figure captions or documentation.

No Comments

No Known Activations