INDEX

Explanations

metaphorical language and scientific terminologies related to variables and coefficients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

-0.42

муж

-0.41

<eos>

-0.40

 CreateTagHelper

-0.39

obenz

-0.38

él

-0.38

↵↵

-0.38

 Brunnen

-0.37

 pide

-0.37

 diph

-0.36

POSITIVE LOGITS

 resourceCulture

0.80

IUrlHelper

0.80

SuppressMessage

0.78

contentLoaded

0.78

')}}">

0.76

Jeografia

0.76

 jspb

0.75

'}>

0.75

principalTable

0.73

 &___

0.73

Activations Density 1.477%

metaphorical language and scientific terminologies related to variables and coefficients

No Comments

No Known Activations