INDEX

Explanations

requests for information and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

aarrggbb

-0.62

 zufolge

-0.57

}\]

-0.52

paravant

-0.49

BaseAdapter

-0.49

снимок

-0.45

EditorBrowsable

-0.44

 convertView

-0.44

RenderAtEndOf

-0.44

 propOrder

-0.44

POSITIVE LOGITS

 >=",

0.75

 kasarigan

0.65

Gambas

0.64

 незавершена

0.64

ècie

0.62

脚注の使い方

0.57

Koordinaten

0.57

CloseOperation

0.56

 pinulongan

0.54

 Roskov

0.54

Activations Density 0.147%

requests for information and interactions

No Comments

No Known Activations