INDEX

Explanations

various instances of the word "format" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

sizeCache

-0.95

 CreateTagHelper

-0.94

 calculées

-0.94

onViewCreated

-0.92

 newOwner

-0.89

Seeker

-0.88

AnchorTagHelper

-0.88

 AssemblyCompany

-0.83

RegistryLite

-0.83

($__

-0.82

POSITIVE LOGITS

 FORMAT

1.62

 format

1.53

 Format

1.48

FORMAT

1.46

 formats

1.43

format

1.41

Format

1.40

formats

1.35

Formats

1.29

 Formats

1.27

Activations Density 0.083%

various instances of the word "format" and its variations in different contexts

No Comments

No Known Activations