INDEX

Explanations

elements indicating familial relationships within texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

TargetException

-0.54

featureID

-0.51

elerik

-0.49

 relation

-0.48

RuleContext

-0.47

Tires

-0.47

რო

-0.47

MENAFN

-0.47

thys

-0.46

BeginContext

-0.46

POSITIVE LOGITS

 незавершена

0.75

 autorytatywna

0.72

 ModelExpression

0.68

 للاسماء

0.63

SerializedName

0.63

DataPropertyName

0.59

#+#

0.59

setViewportView

0.58

KURZBESCHREIBUNG

0.56

 modelAndView

0.55

Activations Density 0.246%

elements indicating familial relationships within texts

No Comments

No Known Activations