INDEX

Explanations

terms related to different types of extracts and their compositions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

adaptiveStyles

-0.71

ftagPool

-0.69

RenderAtEndOf

-0.67

évaluateur

-0.64

PerformLayout

-0.61

AndEndTag

-0.61

SourceChecksum

-0.61

 resourceCulture

-0.61

 HasFactory

-0.58

⟬

-0.58

POSITIVE LOGITS

 extract

0.54

 extracts

0.47

 Extract

0.44

extract

0.41

 extracted

0.41

 extracto

0.41

 processed

0.40

Extract

0.38

 Extracts

0.37

extracted

0.36

Activations Density 0.662%

terms related to different types of extracts and their compositions

No Comments

No Known Activations