INDEX

Explanations

references to data rows in database or data processing contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 majeur

-0.89

))->

-0.85

*/),

-0.85

Anhalt

-0.84

 virtù

-0.83

 &___

-0.81

Datuak

-0.75

lastic

-0.74

 ruines

-0.73

hta

-0.73

POSITIVE LOGITS

Row

1.71

row

1.69

 rows

1.63

ROW

1.51

Row

1.51

row

1.47

 Rows

1.42

rows

1.40

ROW

1.35

Rows

1.31

Activations Density 0.036%

references to data rows in database or data processing contexts

No Comments

No Known Activations