INDEX

Explanations

phrases related to significant events or announcements in a timeline

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

CloseOperation

-0.54

RuleContext

-0.54

soort

-0.52

ódz

-0.50

dolu

-0.49

lankton

-0.49

verifyException

-0.49

Chez

-0.48

 Bantu

-0.48

 Chez

-0.47

POSITIVE LOGITS

 FetchType

0.62

romycin

0.53

 passing

0.50

RUnlock

0.49

 proceeding

0.48

 continuation

0.48

 period

0.48

AddWithValue

0.48

glEnd

0.48

end

0.48

Activations Density 0.136%

phrases related to significant events or announcements in a timeline

No Comments

No Known Activations