INDEX

Explanations

time-related information in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ToAction

-0.76

MeasureSpec

-0.60

 noqa

-0.55

 fuori

-0.54

 SwiftUI

-0.54

RestController

-0.54

 Paglinawan

-0.54

rawDesc

-0.54

 Orrell

-0.53

Mand

-0.52

POSITIVE LOGITS

帖最后由

0.78

UrlResolution

0.69

bibfield

0.66

BibitemShut

0.65

medriver

0.59

AnimationsModule

0.57

NOPQRST

0.57

verläs

0.55

儡

0.55

unicaciones

0.54

Activations Density 0.132%

time-related information in a structured format

No Comments

No Known Activations