INDEX

Explanations

terms related to documentation and file types

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

"Document" or "Doc" file mentions

np_acts-logits-general · gemini-2.0-flash

document foundation

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

ArgsConstructor

-0.78

mergeFrom

-0.72

rrggbb

-0.68

enumii

-0.68

 CreateTagHelper

-0.67

 المعيارى

-0.66

Viitteet

-0.65

makeText

-0.59

raszamy

-0.59

 ActionResult

-0.58

POSITIVE LOGITS

 documents

0.86

DOC

0.86

doc

0.83

DOC

0.78

 Documents

0.77

 Docs

0.74

 Document

0.74

Doc

0.73

 docs

0.71

 document

0.71

Activations Density 0.073%

terms related to documentation and file types

"Document" or "Doc" file mentions

document foundation

No Comments

No Known Activations