INDEX

Explanations

commands or functions related to locating or fetching elements in various contexts

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

"find"

np_acts-logits-general · gemini-2.0-flash

find out

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

setVerticalGroup

-0.71

 betweenstory

-0.67

zzleHttp

-0.64

 mAdapter

-0.63

 سكانية

-0.61

initializeApp

-0.60

 ostavi

-0.60

 Mattel

-0.58

 Schlegel

-0.58

 Mesh

-0.57

POSITIVE LOGITS

find

1.07

Find

1.02

 find

1.02

 FIND

1.01

FIND

1.00

 Find

0.96

 finder

0.84

finder

0.82

Finder

0.82

Finding

0.81

Activations Density 0.224%

commands or functions related to locating or fetching elements in various contexts

"find"

find out

No Comments

No Known Activations