INDEX

Explanations

codes and configuration settings within 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 @ 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

uxxxx

-0.73

 utafitiHapana

-0.72

 auffi

-0.69

glBindBuffer

-0.67

 moschino

-0.65

 nonUne

-0.63

EndGlobalSection

-0.62

ParallelGroup

-0.61

amaño

-0.61

verwijspagina

-0.60

POSITIVE LOGITS

newArrayList

0.60

epy

0.54

Espèce

0.51

ستی

0.50

andy

0.49

ref

0.48

Da

0.48

 combination

0.47

 interiors

0.47

 Carden

0.46

Activations Density 0.158%

codes and configuration settings within a programming context

No Comments

No Known Activations