INDEX

Explanations

terms related to replacement or substitution

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 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

 defStyleAttr

-0.77

sertation

-0.73

 puisse

-0.73

 Италијани

-0.71

 spéciales

-0.71

fortawesome

-0.70

ViewInit

-0.68

zzard

-0.67

)`

-0.67

Portale

-0.66

POSITIVE LOGITS

 Replace

1.52

 replacement

1.44

 replace

1.41

Replace

1.39

 Replacement

1.37

 replacing

1.34

 REPLACE

1.34

Replacing

1.33

 replacements

1.30

REPLACE

1.30

Activations Density 0.167%

terms related to replacement or substitution

No Comments

No Known Activations