INDEX

Explanations

technical terms and references related to software and hardware support

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

developer, browser, client, mobile

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

BufferException

-0.50

LEncoder

-0.43

 désolés

-0.41

tvguidetime

-0.41

styleType

-0.41

Tembelea

-0.39

 DbType

-0.35

migrationBuilder

-0.35

jsonwebtoken

-0.34

 GenerationType

-0.34

POSITIVE LOGITS

AddHtmlAttribute

0.50

 CreateTagHelper

0.47

㈦

0.45

%)$

0.45

principalColumn

0.45

+#+

0.44

 developers

0.43

 developer

0.42

WithMany

0.42

 Developers

0.42

Activations Density 0.088%

technical terms and references related to software and hardware support

developer, browser, client, mobile

No Comments

No Known Activations