INDEX

Explanations

references to parts or sections of objects, documents, or methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

милия

-0.63

 للاسماء

-0.60

xide

-0.59

PyExc

-0.57

 padrões

-0.57

ponses

-0.56

GoogleApiClient

-0.56

المناصب

-0.56

soort

-0.55

POSITIVE LOGITS

 portions

1.18

 portion

1.16

 parts

1.04

 part

1.01

 Portion

0.98

 sections

0.95

 section

0.94

portion

0.92

 segments

0.91

parts

0.90

Activations Density 0.807%

references to parts or sections of objects, documents, or methodologies

No Comments

No Known Activations