INDEX

Explanations

programming terms related to web services and annotations

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

legal citation reporters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TypedDataSet

-0.36

utilisons

-0.36

 Dör

-0.34

LookAnd

-0.34

 celui

-0.30

amélioration

-0.30

libft

-0.29

 régimen

-0.29

_));

-0.29

]=>

-0.29

POSITIVE LOGITS

annotation

1.20

 annotation

0.85

annotations

0.81

 Annotation

0.72

 annotations

0.71

AnchorStyles

0.68

Annotations

0.65

annotate

0.65

Annotation

0.64

notation

0.63

Activations Density 0.000%

programming terms related to web services and annotations

legal citation reporters

No Comments

No Known Activations