INDEX

Explanations

references to code, scripts, or programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

tagHelperRunner

-0.76

 resourceCulture

-0.70

Datuak

-0.69

ViewFeatures

-0.66

("")){

-0.64

BeginInit

-0.63

.*")]

-0.63

 فريبيس

-0.62

+#+

-0.61

 ویکی‌پدیا

-0.61

POSITIVE LOGITS

 (!__

0.86

BagConstraints

0.82

semantics

0.80

EndContext

0.80

LayoutStyle

0.76

 AppCompat

0.76

 actionPerformed

0.68

 RequestMethod

0.57

ẾT

0.56

HandlerContext

0.53

Activations Density 0.026%

references to code, scripts, or programming languages

No Comments

No Known Activations