INDEX

Explanations

specific scientific or technical terms and identifiers, particularly related to biological or medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

]--;

-0.85

Brainz

-0.78

}]{

-0.70

$',

-0.69

ρός

-0.66

brates

-0.65

")));

-0.65

IFICATE

-0.65

enumi

-0.64

ouncements

-0.64

POSITIVE LOGITS

Vidite

0.58

OGND

0.50

0.49

 siguran

0.48

0.47

0.46

 totul

0.46

 tuturor

0.45

Activations Density 0.990%

specific scientific or technical terms and identifiers, particularly related to biological or medical contexts

No Comments

No Known Activations