INDEX

Explanations

terms related to editing and modification

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

do not edit or

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

InlineData

-0.58

 GenerationType

-0.44

windowFixed

-0.44

UrlResolution

-0.40

webElementXpaths

-0.40

LookAnd

-0.39

PYX

-0.39

 PyLong

-0.39

titleMargin

-0.38

Спољашње

-0.38

POSITIVE LOGITS

ocardial

0.54

 calloc

0.52

ConstraintMaker

0.51

]")]

0.49

gdx

0.48

ulemon

0.48

+#+#

0.47

 lateinit

0.47

 vicenda

0.47

ssymb

0.46

Activations Density 0.000%

terms related to editing and modification

do not edit or

No Comments

No Known Activations