INDEX

Explanations

references to rows in data tables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 majeur

-0.92

))->

-0.90

Anhalt

-0.86

*/),

-0.83

 doskon

-0.79

 virtù

-0.79

 Monfieur

-0.78

 ruines

-0.77

DispatchToProps

-0.77

 dernières

-0.77

POSITIVE LOGITS

row

2.32

Row

2.27

row

2.11

Row

2.09

 rows

2.07

ROW

1.93

ROW

1.81

rows

1.81

 Rows

1.78

Rows

1.66

Activations Density 0.036%

references to rows in data tables

No Comments

No Known Activations