INDEX

Explanations

mathematical and programming syntax related to data analysis and modeling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UnusedPrivate

-0.54

LabelTagHelper

-0.52

 تضيفلها

-0.51

aarrggbb

-0.51

 arşivlendi

-0.50

EndGlobalSection

-0.48

AndroidJUnit

-0.48

audiovisuel

-0.47

AddTagHelper

-0.46

WriteTagHelper

-0.44

POSITIVE LOGITS

AutoScaleMode

0.52

IntoConstraints

0.40

numerator

0.40

setVerticalGroup

0.39

 copy

0.36

 OnInit

0.36

 replicate

0.36

 roll

0.36

rav

0.35

참고

0.35

Activations Density 1.734%

mathematical and programming syntax related to data analysis and modeling

No Comments

No Known Activations