INDEX

Explanations

references to segments or portions in a document, particularly in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 NSCoder

-0.86

)");

-0.81

';

-0.79

)";

-0.78

 AssemblyCompany

-0.74

 Diſ

-0.74

HtmlAttribute

-0.74

 distanciation

-0.73

utilisons

-0.73

ESSMENT

-0.73

POSITIVE LOGITS

seg

0.84

 segments

0.74

className

0.58

 segment

0.54

segments

0.54

ClassName

0.53

SEG

0.53

 Segments

0.53

seg

0.52

Ve

0.51

Activations Density 0.093%

references to segments or portions in a document, particularly in a technical context

No Comments

No Known Activations