INDEX

Explanations

the term "usual," indicating a focus on common or standard elements in a context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 NgModule

-1.03

Datuak

-1.01

 nahilalakip

-0.96

ResumeLayout

-0.96

Hochspringen

-0.96

 HttpHeaders

-0.95

 Normdatei

-0.95

 kasarigan

-0.94

IVEREF

-0.93

 '\\;'

-0.91

POSITIVE LOGITS

 usual

1.40

usual

1.23

 Usual

1.14

Usual

0.98

 üblichen

0.94

 habituales

0.67

 customary

0.61

 familiar

0.61

 привы

0.56

いつもの

0.56

Activations Density 0.139%

the term "usual," indicating a focus on common or standard elements in a context

No Comments

No Known Activations