INDEX

Explanations

reflexive pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 nuvem

-0.54

 moglie

-0.53

Intrinsic

-0.53

 Hälfte

-0.53

 Baruch

-0.53

gyz

-0.53

mstyle

-0.52

 Fiske

-0.52

 Lowe

-0.52

hiro

-0.51

POSITIVE LOGITS

InjectAttribute

0.71

parsedMessage

0.69

 €)

0.67

 AssemblyCulture

0.65

^*)

0.65

 encontraban

0.64

styleType

0.64

')")

0.64

AddHtmlAttribute

0.62

Demikian

0.62

Activations Density 0.107%

reflexive pronouns

No Comments

No Known Activations