INDEX

Explanations

references to specific programming or technical terms related to software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

SourceChecksum

-1.30

parsedMessage

-1.02

AndEndTag

-1.02

ftagPool

-1.00

AddTagHelper

-0.99

ⓧ

-0.98

elemField

-0.97

XmlAccessType

-0.93

 tartalomajánló

-0.92

FunctionFlags

-0.89

POSITIVE LOGITS

 BoxDecoration

0.53

 draw

0.50

 drawing

0.47

Drawing

0.47

 youngest

0.45

Rounding

0.45

 drawings

0.45

 drawn

0.44

 draws

0.43

ശ

0.43

Activations Density 0.005%

references to specific programming or technical terms related to software development

No Comments

No Known Activations