INDEX

Explanations

references to tutorials and guides

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

DockStyle

-0.72

 Réponses

-0.68

StoryboardSegue

-0.68

 doInBackground

-0.67

tvguidetime

-0.66

 Stunde

-0.66

 EClass

-0.62

 Songtext

-0.61

 NgModule

-0.60

Xna

-0.59

POSITIVE LOGITS

 https

0.64

 http

0.63

ViewFeatures

0.58

0.57

↓↓

0.55

⤵

0.55

0.54

https

0.54

http

0.53

↓

0.49

Activations Density 0.354%

references to tutorials and guides

No Comments

No Known Activations