INDEX

Explanations

occurrences of the prefix "pre" in various contexts

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

prefix "pre"

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

bootstrapcdn

-0.67

ScopeManager

-0.62

 HasFactory

-0.56

 userModel

-0.54

存于互联网档案馆

-0.53

yntaxException

-0.53

ฉัน

-0.52

Figura

-0.52

TokenNameLPAREN

-0.50

AndView

-0.50

POSITIVE LOGITS

pre

1.16

Pre

1.07

Pre

1.02

PRE

0.97

pre

0.95

PRE

0.93

 pré

0.85

 before

0.72

 Pré

0.70

before

0.69

Activations Density 0.026%

occurrences of the prefix "pre" in various contexts

prefix "pre"

No Comments

No Known Activations