INDEX

Explanations

elements related to specific mathematical or computational constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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



-0.82

StoryboardSegue

-0.75

 betweenstory

-0.66

parsedMessage

-0.64

 NSCoder

-0.63

 ModelExpression

-0.58

+#+#

-0.57

 ModelRenderer

-0.56

__::

-0.56

enterOuterAlt

-0.55

POSITIVE LOGITS

0.41

0.40

0.38

0.37

ll

0.37

few

0.36

0.35

Activations Density 0.814%

elements related to specific mathematical or computational constructs

No Comments

No Known Activations