INDEX

Explanations

occurrences of the word "on" in various contexts

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

function or event names

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

NetworkInfo

-0.44

glLoadIdentity

-0.42

 HasFactory

-0.40

SizeF

-0.38

 виправивши

-0.37

URLException

-0.36

 bây

-0.36

PMailer

-0.36

 sekarang

-0.36

now

-0.36

POSITIVE LOGITS

posedge

0.64

OGND

0.59

ondis

0.52

üyada

0.52

 sirena

0.49

 באתר

0.49

 OnTrigger

0.47

IBAction

0.47

 onboarding

0.46

 Handling

0.46

Activations Density 0.007%

occurrences of the word "on" in various contexts

function or event names

No Comments

No Known Activations