INDEX

Explanations

references to computational or technical concepts often used in programming or algorithms

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

↵

-0.58

-0.56

↵↵

-0.54

-0.51

-0.50

oo

-0.48

 Sonne

-0.48

)))

-0.48

POSITIVE LOGITS

NOPQRST

0.92

 AssemblyCulture

0.90

nasium

0.89

RetentionPolicy

0.85

 EconPapers

0.83

moiselle

0.81

 فريبيس

0.80

 HttpNotFound

0.79

 يتيمه

0.79

 vostri

0.79

Activations Density 0.417%

references to computational or technical concepts often used in programming or algorithms

No Comments

No Known Activations