INDEX

Explanations

structural components and attributes of code or data formatting

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

variable name suffixes

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

 Numerade

-0.50

niosek

-0.45

UnusedPrivate

-0.44

 enkelte

-0.42

 Dumnezeu

-0.38

 trasladado

-0.37

 ferdig

-0.37

 undangan

-0.37

 Sanderson

-0.37

mektedir

-0.37

POSITIVE LOGITS

RenderAtEndOf

0.80

RuleContext

0.66

 CreateTagHelper

0.61

 estekak

0.60

 HasFactory

0.55

 كومونز

0.52

 صوتيه

0.51

 autorytatywna

0.51

 resourceCulture

0.48

styleType

0.48

Activations Density 0.037%

structural components and attributes of code or data formatting

variable name suffixes

No Comments

No Known Activations