INDEX

Explanations

terms related to medical or health-related parameters and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

']))

-0.58

')))

-0.57

 *)__

-0.56

>{{

-0.54

}")]

-0.54

))}

-0.54

wirtschaft

-0.54

']>;

-0.52

\{\\

-0.52

richtung

-0.52

POSITIVE LOGITS

1.50

-£

0.80

®-

0.79

-|

0.76

0.75

Efq

0.74

-!

0.73

-...

0.73

 Cæsar

0.72

<bos>

0.72

Activations Density 0.538%

terms related to medical or health-related parameters and statistics

No Comments

No Known Activations