INDEX

Explanations

terms related to comments and comment management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

FailureListener

-0.56

AntiForgeryToken

-0.51

NameInMap

-0.50

 apellidos

-0.49

 resultMap

-0.46

 minOccurs

-0.46

 ModelExpression

-0.45

UnusedPrivate

-0.45

حديد

-0.45

leaner

-0.44

POSITIVE LOGITS

 TextAppearance

0.67

RenderAtEndOf

0.67

 للمعارف

0.66

 chimique

0.66

iastes

0.60

 HttpNotFound

0.59

 censorship

0.59

orite

0.58

 stitches

0.58

BufferException

0.56

Activations Density 0.208%

terms related to comments and comment management

No Comments

No Known Activations