INDEX

Explanations

numerical data and statistics related to populations and demographics

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.20

1:0.03

2:0.16

3:0.06

4:0.04

5:0.13

6:0.04

7:0.04

8:0.04

9:0.03

10:0.15

11:0.02

Negative Logits

 mileage

-2.18

 favorable

-2.14

 timing

-2.07

 competition

-2.06

 previews

-2.06

 preview

-2.03

 tast

-2.02

 predictions

-2.02

 warranties

-2.02

 incentives

-1.98

POSITIVE LOGITS

ithmetic

2.01

lyn

1.98

byss

1.94

raq

1.94

 exorc

1.92

 incre

1.89

Dru

1.89

ッド

1.88

fell

1.86

 Cree

1.85

Activations Density 0.048%

numerical data and statistics related to populations and demographics

No Comments

No Known Activations