INDEX

Explanations

references to high-quality attributes or achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ditor

-0.67

ficulty

-0.66

tagHelperRunner

-0.58

loger

-0.58

Према

-0.57

otry

-0.57

 "..\..\..\

-0.56

ukone

-0.54

sud

-0.53

帖最后由

-0.53

POSITIVE LOGITS

TagMode

0.61

 habituellement

0.55

PI

0.54

 onData

0.53

 contributes

0.53

 infographics

0.52

 contributing

0.52

 NDEBUG

0.52

 arras

0.52

 corresponden

0.51

Activations Density 0.175%

references to high-quality attributes or achievements

No Comments

No Known Activations