INDEX

Explanations

elements related to programming syntax and operations, particularly involving containers and data manipulation

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

Code comparisons (lhs, rhs)

np_acts-logits-general · gemini-2.0-flash

leading and trailing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ConstraintMaker

-0.63

TagMode

-0.57

 north

-0.54

 quadruple

-0.54

WEBPACK

-0.52

 appellant

-0.52

 offensive

-0.51

周一

-0.51

!*\

-0.51

 simplifié

-0.51

POSITIVE LOGITS

setVerticalGroup

0.89

 oprot

0.70

PRNewswire

0.62

 onPostExecute

0.61

PostInfinity

0.60

easeOut

0.56

 مشين

0.55

帖最后由

0.54

UpInside

0.54

postValue

0.53

Activations Density 0.493%

elements related to programming syntax and operations, particularly involving containers and data manipulation

Code comparisons (lhs, rhs)

leading and trailing

No Comments

No Known Activations