INDEX

Explanations

key technical terms and concepts related to research methodologies and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

oredCriteria

-0.87

 виправивши

-0.78

SourceChecksum

-0.73

 pronti

-0.65

følgelig

-0.61

 AssemblyCompany

-0.61

 bezeichneter

-0.61

LookAnd

-0.60

 facie

-0.60

 Ignorance

-0.59

POSITIVE LOGITS

 rather

0.90

 instead

0.83

 unlike

0.77

unlike

0.72

rather

0.72

 Rather

0.71

而非

0.71

instead

0.70

而不是

0.69

Rather

0.68

Activations Density 0.775%

key technical terms and concepts related to research methodologies and frameworks

No Comments

No Known Activations