INDEX

Explanations

sections of text that indicate structured data or metadata format

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

DOCTYPE

-0.73

es

-0.73

complexContent

-0.72

formKey

-0.70

endmodule

-0.70

fanart

-0.70

 IERC

-0.69

featureID

-0.67

ThroughAttribute

-0.66

Pim

-0.66

POSITIVE LOGITS

1.80

1.49

1.43

1.41

1.39

1.37

1.31

1.27

1.23

1.19

Activations Density 0.064%

sections of text that indicate structured data or metadata format

No Comments

No Known Activations