INDEX

Explanations

symbols and characters related to HTML or web markup

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

the ampersand character (&) and HTML entities containing ampersands.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/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.31.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

bootstrapcdn

-0.46

AsUp

-0.43

 '\\;'

-0.40

ⓧ

-0.34

 canst

-0.33

LLocation

-0.33

 Meksiku

-0.32

estacks

-0.32

 tribune

-0.31

\}}

-0.31

POSITIVE LOGITS

amp

1.08

nbsp

0.86

quot

0.84

lt

0.82

amp

0.72

(&

0.70

Amp

0.70

("&

0.67

;&

0.65

\&

0.64

Activations Density 0.098%

symbols and characters related to HTML or web markup

the ampersand character (&) and HTML entities containing ampersands.

No Comments

No Known Activations