INDEX

Explanations

content related to regulations and proposed rules, particularly in environmental and occupational safety contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+

-0.76

 незавершена

-0.65

الإنجليزية

-0.59

 utafitiHapana

-0.58

 AssemblyVersion

-0.57

moveToFirst

-0.56

BeginContext

-0.56

lencia

-0.56

printStackTrace

-0.56

:+:

-0.55

POSITIVE LOGITS

 rule

0.87

 draft

0.81

 Notice

0.80

rule

0.79

 Draft

0.76

 promulg

0.76

 propOrder

0.75

RegistryLite

0.75

 notice

0.75

Notice

0.73

Activations Density 0.568%

content related to regulations and proposed rules, particularly in environmental and occupational safety contexts

No Comments

No Known Activations