INDEX

Explanations

references to specific entities or concepts, particularly those that are unique or significant in context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewSet

-0.55

${

-0.49

<sup>

-0.47

essler

-0.43

thag

-0.43

 Estadística

-0.42

helf

-0.42

 schedule

-0.41

cionario

-0.41

uldron

-0.40

POSITIVE LOGITS

IsContent

0.88

AndEndTag

0.85

EndProject

0.82

 فريبيس

0.80

InSection

0.78

CloseOperation

0.77

 HasFactory

0.76

LookAnd

0.74

IntoConstraints

0.73

RegistryLite

0.72

Activations Density 0.316%

references to specific entities or concepts, particularly those that are unique or significant in context

No Comments

No Known Activations