INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.7.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

0:0.07

1:0.09

2:0.08

3:0.10

4:0.07

5:0.08

6:0.08

7:0.09

8:0.10

9:0.07

10:0.06

11:0.08

Negative Logits

�

-2.21

isp

-2.13

ェ

-2.05

enses

-1.98

asion

-1.97

uci

-1.97

�

-1.96

itivity

-1.95

sense

-1.95

�

-1.88

POSITIVE LOGITS

 pamph

2.28

 medic

2.13

 stret

2.11

 gymn

2.10

 Canaver

2.06

 besie

2.02

 surgeons

1.97

 Mondays

1.96

 benches

1.95

 Sundays

1.94

Activations Density 0.000%

No Known Activations

This feature has no known activations.