INDEX

Explanations

rankings and evaluations of programs, vehicles, or attributes

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

 متعلقه

-0.89

 unknownFields

-0.87

Personensuche

-0.75

 disambiguazione

-0.75

 AssemblyCulture

-0.73

LookAnd

-0.73

новниш

-0.73

 myſelf

-0.72

tagHelperRunner

-0.69

henswürdigkeiten

-0.68

POSITIVE LOGITS

top

1.99

 ranked

1.76

 ranking

1.64

top

1.61

 rank

1.56

 tops

1.54

Top

1.53

 topping

1.47

Top

1.47

ranked

1.43

Activations Density 0.303%

rankings and evaluations of programs, vehicles, or attributes

No Comments

No Known Activations