INDEX

Explanations

references to programming constructs and operations in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 spanned

-0.56

进制

-0.56

 demografica

-0.56

帖最后由

-0.52

IVEREF

-0.50

taje

-0.49

 ellers

-0.48

chutz

-0.47

ppsala

-0.47

ImageContext

-0.47

POSITIVE LOGITS

 Idle

0.77

 }}"></

0.69

 idle

0.66

 rootReducer

0.64

BindView

0.63

:+:

0.61

ggiato

0.61

\{\\

0.60

这不

0.60

oring

0.59

Activations Density 2.403%

references to programming constructs and operations in code snippets

No Comments

No Known Activations