INDEX

Explanations

names and proper nouns, particularly those related to people and places

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

 Havel

-0.99

glades

-0.89

 Sailor

-0.87

HST

-0.85

 PACE

-0.83

 Shakspeare

-0.82

 Draper

-0.81

Efq

-0.78

$")

-0.77

Dover

-0.76

POSITIVE LOGITS

 Jerome

0.79

 Sheridan

0.77

 Sherwood

0.75

Jerome

0.73

 Curry

0.73

 cherchés

0.73

Sharma

0.72

::{

0.71

corr

0.70

 المعيارى

0.69

Activations Density 1.630%

names and proper nouns, particularly those related to people and places

No Comments

No Known Activations