INDEX

Explanations

numerical data or statistics within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Finally

-0.58

Finally

-0.54

finally

-0.53

 finally

-0.51

 سكانية

-0.49

 utafitiHapana

-0.49

ilstein

-0.48

 mixing

-0.47

 mezclar

-0.46

flix

-0.46

POSITIVE LOGITS

 ExecuteAsync

0.98

sidemargin

0.80

UnsafeEnabled

0.79

 AttributeSet

0.69

setVerticalGroup

0.69

ViewFeatures

0.67

 EconPapers

0.66

 Normdatei

0.66

OGND

0.64

NewReader

0.63

Activations Density 1.476%

numerical data or statistics within the text

No Comments

No Known Activations