INDEX

Explanations

references to a research context or findings related to a study

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

Sentences starting with "We"

np_acts-logits-general · gemini-2.0-flash

verbs following We

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

rawDesc

-0.74

لاعات

-0.61

 كومونز

-0.59

rxjs

-0.58

 kaarangay

-0.57

abilia

-0.57

styleType

-0.56

RectangleBorder

-0.56

mitive

-0.55

duate

-0.55

POSITIVE LOGITS

 resourceCulture

0.86

 want

0.71

had

0.70

 would

0.66

 also

0.66

 always

0.65

 really

0.64

 will

0.64

 have

0.64

 still

0.64

Activations Density 1.110%

references to a research context or findings related to a study

Sentences starting with "We"

verbs following We

No Comments

No Known Activations