INDEX

Explanations

references to specific attributes or characteristics within structured data, such as documents, names, or coding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

^(@)

-1.35

NUMX

-1.21

\<^

-1.16

>\<^

-1.13

$_"

-1.10

 चीज़ों

-1.10

rawDesc

-1.09

 ་་

-1.08

 wireType

-1.06

 صوتيه

-1.06

POSITIVE LOGITS

<eos>

1.58

↵↵

1.47

↵

1.36

1.13

is

1.09

↵↵↵

1.08

↵↵↵↵

1.08

0.99

has

0.96

0.90

Activations Density 1.926%

references to specific attributes or characteristics within structured data, such as documents, names, or coding elements

No Comments

No Known Activations