INDEX

Explanations

programming-related terms and code snippets involving data structures

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

Target

-0.40

{{{

-0.37

 Target

-0.37

ofan

-0.37

zug

-0.37

//}

-0.37

REAM

-0.36

context

-0.35

 tương

-0.35

커

-0.34

POSITIVE LOGITS

enterOuterAlt

0.79

AddHtmlAttribute

0.70

+:+

0.70

 AttributeSet

0.69

AttributeSet

0.68

URLException

0.67

ArgsConstructor

0.67

 betweenstory

0.67

ométrique

0.66

 upvote

0.65

Activations Density 0.813%

programming-related terms and code snippets involving data structures

No Comments

No Known Activations