INDEX

Explanations

positive feedback and experiences related to service or interactions

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

work withstart toto understandto updateI know

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

addPreferredGap

-0.47

RTLR

-0.42

 Мексичка

-0.42

tonode

-0.41

 يتيمه

-0.40

 familiare

-0.39

 ApiClient

-0.39

MethodManager

-0.38

 beroep

-0.38

endpush

-0.37

POSITIVE LOGITS

AISSEE

0.59

UnusedPrivate

0.54

 onCreateView

0.43

ngdoc

0.40

exitRule

0.40

MigrationBuilder

0.39

horesis

0.38

httphttps

0.38

apuram

0.38

 BoxFit

0.38

Activations Density 0.008%

positive feedback and experiences related to service or interactions

work withstart toto understandto updateI know

No Comments

No Known Activations