INDEX

Explanations

references to columns and their attributes in a dataset or scientific context

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

"column" or "columns"

np_acts-logits-general · gemini-2.0-flash

column or columnar

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Réponses

-0.84

]--;

-0.76

]++;

-0.67

ChildScrollView

-0.66

posedge

-0.65

asteroide

-0.60

anyahu

-0.57

PLW

-0.57

RectangleBorder

-0.57

揄

-0.56

POSITIVE LOGITS

 columns

0.88

 Columns

0.82

 Column

0.79

columns

0.79

setColumn

0.66

 getColumn

0.65

getColumn

0.65

 فق

0.63

UMNS

0.63

ized

0.63

Activations Density 0.040%

references to columns and their attributes in a dataset or scientific context

"column" or "columns"

column or columnar

No Comments

No Known Activations