INDEX

Explanations

mathematical terms and expressions related to functional analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

RenderAtEndOf

-0.80



-0.77

ItemBackground

-0.76

principalTable

-0.66

iastes

-0.63

adaptiveStyles

-0.62

abestanden

-0.60

 الحره

-0.58

addCriterion

-0.57

SizeMode

-0.56

POSITIVE LOGITS

\|

1.07

$\|

1.07

}\|

1.05

$|

1.05

||

1.05

1.03

0.99

}{|

0.99

abs

0.98

||

0.97

Activations Density 1.574%

mathematical terms and expressions related to functional analysis

No Comments

No Known Activations