INDEX

Explanations

mentions of specific geographical locations and political entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

riscoll

-0.54

Personensuche

-0.51

atimes

-0.48

MENAFN

-0.47

higen

-0.46

Bson

-0.45

евич

-0.45

вич

-0.44

types

-0.44

ombe

-0.44

POSITIVE LOGITS

########.

0.92

featureID

0.74

 FetchType

0.72

RTEE

0.71

 CURIAM

0.63

IntoConstraints

0.60

 mapStateToProps

0.59

 fotografico

0.58

 createState

0.58

Efq

0.58

Activations Density 0.300%

mentions of specific geographical locations and political entities

No Comments

No Known Activations