INDEX

Explanations

language related to legal terminology and conditions

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

MockBean

-0.56

 статистики

-0.49

developed

-0.49

DataColumn

-0.45

 Montero

-0.45

findpost

-0.45

 passaram

-0.44

 Ceramby

-0.42

 Einsch

-0.42

ونز

-0.41

POSITIVE LOGITS

 defaults

0.82

 Defaults

0.72

 default

0.67

 pinulongan

0.67

 AssemblyCulture

0.64

ANDUM

0.63

WithIOException

0.63

 Undefined

0.61

 Crusoe

0.61

ukone

0.60

Activations Density 0.592%

language related to legal terminology and conditions

No Comments

No Known Activations