INDEX

Explanations

elements related to sharing personal reading experiences and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

TagMode

-0.76

 kasarigan

-0.75

///</

-0.57

Identyfik

-0.57

ItemBackground

-0.56

__*/

-0.56

UrlResolution

-0.55

Datuak

-0.55

findpost

-0.53

HostException

-0.53

POSITIVE LOGITS

tagHelperRunner

0.61

JspWriter

0.50

اتها

0.47

λλα

0.47

 getDescription

0.46

δέ

0.46

ActionCreators

0.45

hlon

0.45

RefreshLayout

0.45

Activations Density 1.057%

elements related to sharing personal reading experiences and preferences

No Comments

No Known Activations