INDEX

Explanations

terms related to ranking or hierarchical ordering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

évaluateur

-0.83

_('

-0.74

PLW

-0.73

Eds

-0.70

coaster

-0.69

 Drog

-0.68

Ctx

-0.67

rachtet

-0.67

 Avila

-0.67

ITTEN

-0.67

POSITIVE LOGITS

 RANK

1.56

 Rankin

1.43

 ranks

1.40

 Ranks

1.36

RANK

1.33

 Rank

1.32

Rank

1.32

 rank

1.29

Ranks

1.27

rank

1.23

Activations Density 0.063%

terms related to ranking or hierarchical ordering

No Comments

No Known Activations