INDEX

Explanations

keywords and concepts related to programming templates and structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 ſever

-0.62

ValueStyle

-0.61

 Shaksp

-0.61

 îng

-0.57

 ſmall

-0.57

 ſtre

-0.56

 houſe

-0.55

 Chriſt

-0.55

 ſhe

-0.54

 Diſ

-0.53

POSITIVE LOGITS

amenta

0.67

 IBOutlet

0.62

]$}

0.62

(;;

0.61

 constexpr

0.58

 snippetHide

0.57

hele

0.56

canes

0.56

 endwhile

0.56

bonnet

0.56

Activations Density 0.594%

keywords and concepts related to programming templates and structures

No Comments

No Known Activations