INDEX

Explanations

references to specific methods or processes within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 الحره

-0.74

SequentialGroup

-0.61

hésite

-0.57

writeFieldEnd

-0.56

 estekak

-0.50

 vulgaires

-0.50

はじめに

-0.50

انيف

-0.49

 <=",

-0.47

⋙

-0.46

POSITIVE LOGITS

<?

0.63

PerformLayout

0.59

onOptions

0.59

createCanvas

0.58

 HasFactory

0.56

sidemargin

0.56

 vVar

0.56

classnames

0.53

isNameExpr

0.53

nasel

0.52

Activations Density 0.648%

references to specific methods or processes within a text

No Comments

No Known Activations