INDEX

Explanations

terms indicating the process of selection or choosing

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

after "select" or "selection"

np_acts-logits-general · gemini-2.0-flash

selecting options or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 webView

-0.64

RunAsync

-0.64

 Audiodateien

-0.62

Демографія

-0.61

osoba

-0.60

]='\

-0.59

 vVar

-0.58

ecake

-0.57

electricity

-0.57

ervations

-0.57

POSITIVE LOGITS

 lọc

0.80

deselect

0.68

ByPrimaryKey

0.66

picker

0.63

er

0.60

 Sele

0.59

 Seitz

0.57

 Picking

0.56

 picks

0.56

 criteria

0.56

Activations Density 0.075%

terms indicating the process of selection or choosing

after "select" or "selection"

selecting options or items

No Comments

No Known Activations