INDEX

Explanations

references to low attributes, particularly in relation to quality or metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 servici

-0.86

 financières

-0.85

 virtù

-0.84

 véhic

-0.84

 religieuses

-0.83

GOTREF

-0.81

 religieux

-0.81

 européennes

-0.80

 Mundi

-0.80

 supérieurs

-0.79

POSITIVE LOGITS

Low

1.71

LOW

1.71

low

1.66

Low

1.56

 Lowry

1.41

low

1.40

LOW

1.27

低

1.17

 Lowe

1.16

 lows

1.13

Activations Density 0.099%

references to low attributes, particularly in relation to quality or metrics

No Comments

No Known Activations