INDEX

Explanations

references to parts or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

")));

-0.97

(!__

-0.94

"]));

-0.93

PerformLayout

-0.93

)});

-0.90

GraphicsUnit

-0.89

তথ্যসূত্র

-0.86

 חיצוניים

-0.86

 Hald

-0.85

 للمعارف

-0.84

POSITIVE LOGITS

 pieces

1.62

Pieces

1.54

 Pieces

1.47

 piece

1.43

 Piece

1.33

Piece

1.28

 PIECE

1.28

pieces

1.23

piece

1.10

stück

1.07

Activations Density 0.044%

references to parts or components

No Comments

No Known Activations