INDEX

Explanations

elements related to technical specifications or complexities in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 itſelf

-0.72

 poffe

-0.64

 мәкалә

-0.63

Efq

-0.63

 themſelves

-0.60

 Anſ

-0.59

 Jefus

-0.59

yeezy

-0.58

(\<

-0.56

$_"

-0.56

POSITIVE LOGITS

InjectAttribute

0.65

fillType

0.61

 Besoin

0.54

IsMutable

0.54

phazard

0.53

oader

0.52

*/),

0.51

oa̍t

0.50

ScopeManager

0.50

aternion

0.49

Activations Density 0.362%

elements related to technical specifications or complexities in discussions

No Comments

No Known Activations