INDEX

Explanations

technical terms and code-related components in a programming context

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

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

oxone

-0.56

rawDesc

-0.54

 snippetHide

-0.53

Sheet

-0.53

]<<

-0.49

Manbalar

-0.49

ABAD

-0.49

zule

-0.48

 DriverManager

-0.48

зий

-0.48

POSITIVE LOGITS

 column

0.68

 cell

0.59

DataColumn

0.58

 getWidth

0.57

 columns

0.56

Cell

0.55

column

0.53

Column

0.53

sortable

0.53

cells

0.52

Activations Density 0.112%

technical terms and code-related components in a programming context

No Comments

No Known Activations