INDEX

Explanations

phrases that indicate membership or association

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

enumi

-0.65

bnf

-0.58

 compris

-0.48

âng

-0.48

 most

-0.46

oznam

-0.45

sun

-0.45

ेद

-0.44

 types

-0.44

CAPTION

-0.44

POSITIVE LOGITS

 للاسماء

0.76

errHandler

0.75

ThroughAttribute

0.73

XmlAccessType

0.72

 Lokales

0.71

HideFlags

0.71

WebMethod

0.71

ⓧ

0.70

 htons

0.68

 umbi

0.68

Activations Density 0.151%

phrases that indicate membership or association

No Comments

No Known Activations