INDEX

Explanations

the prefix "ra" in various word forms

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

Follows "ra" or "Ram"

np_acts-logits-general · gemini-2.0-flash

ra- words

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

 AssemblyCompany

-0.61

getSubject

-0.58

EndProject

-0.57

PEND

-0.55

 dtype

-0.54

 COMMIT

-0.53

 OkHttpClient

-0.52

 keny

-0.52

commit

-0.51

 committed

-0.50

POSITIVE LOGITS

 Telerik

0.68

 Wraith

0.66

NullException

0.62

GTP

0.62

 Raptor

0.60

 grecque

0.60

 uſed

0.58

transQ

0.57

 Bradbury

0.57

 Rauch

0.57

Activations Density 0.148%

the prefix "ra" in various word forms

Follows "ra" or "Ram"

ra- words

No Comments

No Known Activations