INDEX

Explanations

references to specific individuals and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

/**

-0.68

ridor

-0.68

Criter

-0.67

ام

-0.67

 Woodruff

-0.67

Pei

-0.67

 Villar

-0.66

zette

-0.65

 Marley

-0.64

ामी

-0.64

POSITIVE LOGITS

PerformLayout

0.93

quelize

0.92

 Gild

0.86

 bershka

0.84

+:+

0.82

 blessé

0.81

 Unilever

0.78

WAUKEE

0.78

 Westport

0.76

σσ

0.74

Activations Density 2.995%

references to specific individuals and locations

No Comments

No Known Activations