INDEX

Explanations

specific identifiers or markers in coded data or programming structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 exploring

-0.57

 Hawkins

-0.54

 Paglinawan

-0.53

[]{"

-0.53

大了

-0.52

 Goodrich

-0.52

ட்டி

-0.52

[]{

-0.51

 يتيمه

-0.51

POSITIVE LOGITS

]")]

0.86

 }}$}

0.84

存于互联网档案馆

0.76

 NSCoder

0.73

 ModelExpression

0.72

 ControllerBase

0.72

՚

0.70

 Normdatei

0.69

CORBA

0.68

itinéraire

0.66

Activations Density 0.187%

specific identifiers or markers in coded data or programming structure

No Comments

No Known Activations