INDEX

Explanations

words related to completion and attempts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ctx

-0.71

-0.70

 Trilogy

-0.70

 ILogger

-0.65

MatInputModule

-0.65

XtraBars

-0.65

مصادر

-0.63

 "'");

-0.63

ViewInit

-0.62

 Normdatei

-0.58

POSITIVE LOGITS

 Nascimento

0.92

 Parac

0.86

 qashqai

0.85

 Copernicus

0.82

 previa

0.81

 uchiha

0.79

 Uchiha

0.78

 Pelham

0.78

 Cornelius

0.77

 Peralta

0.77

Activations Density 0.090%

words related to completion and attempts

No Comments

No Known Activations