INDEX

Explanations

references to coding functions and methods within programming contexts

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

$(document).ready queries

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

AntiForgeryToken

-0.51

interopRequire

-0.46

parsedMessage

-0.45

 typelib

-0.45

Diweddarwch

-0.43

 τρό

-0.43

guien

-0.42

 []).

-0.42

httphttps

-0.41

 nonUne

-0.41

POSITIVE LOGITS

withOpacity

0.54

ropoda

0.47

styleable

0.45

tagHelperRunner

0.42

basicConfig

0.41

Билгалдахарш

0.41

lopen

0.40

eqnarray

0.39

 ReactDOM

0.39

 crossorigin

0.38

Activations Density 0.001%

references to coding functions and methods within programming contexts

$(document).ready queries

No Comments

No Known Activations