INDEX

Explanations

references to bonuses and additional rewards

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cdk

-0.55

 semis

-0.55

 kautta

-0.51

 AssemblyVersion

-0.50

éně

-0.50

cjonal

-0.50

{_

-0.50

itect

-0.50

AddTagHelper

-0.49

bearer

-0.49

POSITIVE LOGITS

 holes

0.77

 Allah

0.75

 hole

0.75

 Holes

0.70

 MainActivity

0.70

Демографія

0.66

 OkHttpClient

0.66

 kasarigan

0.64

 MonoBehaviour

0.63

 bonus

0.63

Activations Density 0.215%

references to bonuses and additional rewards

No Comments

No Known Activations