INDEX

Explanations

specific named entities or important terms relevant to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 صوتيه

-0.79

достатки

-0.77

cyjna

-0.75

cyjny

-0.74

 Jazeera

-0.74

 HttpNotFound

-0.74

 Moines

-0.72

 CascadeType

-0.71

 становника

-0.71

othesis

-0.70

POSITIVE LOGITS

 Diſ

1.01

withstanding

0.99

 Perſ

0.99

 itſelf

0.96

 Reſ

0.95

 purpoſe

0.93

 Majefty

0.93

ſelf

0.93

 themſelves

0.91

 Monfieur

0.91

Activations Density 1.197%

specific named entities or important terms relevant to various subjects

No Comments

No Known Activations