INDEX

Explanations

terminologies and phrases related to political affiliations and communications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 كومونز

-0.62

noopener

-0.57

 UITableViewCell

-0.56

UFACT

-0.56

uyez

-0.56

^(@)

-0.55

>\<^

-0.55

iosync

-0.54

ịp

-0.53

kug

-0.53

POSITIVE LOGITS

 […]

1.94

↵

1.93

 [...]

1.43

1.34

,...

1.34

↵↵

1.34

</h3>

1.31

[…]

1.28

...

1.27

[...]

1.25

Activations Density 9.051%

terminologies and phrases related to political affiliations and communications

No Comments

No Known Activations