INDEX

Explanations

numerical identifiers or references in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 overwhelming

-0.52

raw

-0.52

 impres

-0.51

anea

-0.50

})();

-0.50

imov

-0.49

rootNode

-0.48

gorov

-0.44

varez

-0.44

pmatrix

-0.44

POSITIVE LOGITS

 BorderRadius

0.71

RenderAtEndOf

0.69

extAlignment

0.68

 المعيارى

0.66

PostExecute

0.66

日閲覧

0.66

 requestCode

0.61

rungsseite

0.60

 BoxFit

0.60

 forState

0.60

Activations Density 0.184%

numerical identifiers or references in research contexts

No Comments

No Known Activations