INDEX

Explanations

attributes and qualities of products

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

Something included; often "case" or "cap"

np_acts-logits-general · gemini-2.0-flash

accessories and components

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

 doInBackground

-0.66

Jeografia

-0.62

RegressionTest

-0.60

berdayakan

-0.58

 rimasto

-0.57

 popolari

-0.56

ContentAsync

-0.55

 dumne

-0.52

 parseFrom

-0.52

 ferons

-0.51

POSITIVE LOGITS

 carrying

0.82

 cover

0.77

AndEndTag

0.76

 Carrying

0.75

Carrying

0.74

 protective

0.74

 instruction

0.72

 optional

0.70

carrying

0.70

 holder

0.70

Activations Density 0.205%

attributes and qualities of products

Something included; often "case" or "cap"

accessories and components

No Comments

No Known Activations