INDEX

Explanations

terminology associated with evaluations or judgments in legal or mathematical contexts

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

таратура

-0.49

Cyfeiriadau

-0.48

Hentet

-0.45

ग्री

-0.41

chene

-0.41

aba

-0.41

kani

-0.41

 Enciclopedia

-0.41

POSITIVE LOGITS

WebServlet

0.81

 متعلقه

0.75

 myſelf

0.73

HideFlags

0.72

 ſind

0.72

ſelf

0.71

NUMX

0.70

 defStyleAttr

0.68

]--;

0.68

neſs

0.68

Activations Density 2.930%

terminology associated with evaluations or judgments in legal or mathematical contexts

No Comments

No Known Activations