INDEX

Explanations

titles or names associated with animated series and movies

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

 myſelf

-1.54

RegressionTest

-1.43

 itſelf

-1.39

 ―――――

-1.37

."));

-1.36

__":

-1.36

__':

-1.35

Rhestr

-1.35

}\]

-1.34

")){

-1.34

POSITIVE LOGITS

1.16

0.90

0.85

0.84

0.82

0.80

0.79

0.76

0.74

Activations Density 0.600%

titles or names associated with animated series and movies

No Comments

No Known Activations