INDEX

Explanations

programming syntax related to variable assignments and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 repeat

-0.39

 repeating

-0.36

 always

-0.35

 supérieures

-0.35

AsUp

-0.35

endif

-0.33

Repeat

-0.33

 virus

-0.31

 comportements

-0.31

 Sociales

-0.31

POSITIVE LOGITS

 defaultstate

0.73

+#+

0.72

OGND

0.68

SequentialGroup

0.67

twimg

0.65

errHandler

0.63

parsedMessage

0.63

 snippetHide

0.61

SourceChecksum

0.60

Personendaten

0.60

Activations Density 0.097%

programming syntax related to variable assignments and function definitions

No Comments

No Known Activations