INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

0:0.08

1:0.12

2:0.09

3:0.08

4:0.08

5:0.07

6:0.06

7:0.09

8:0.07

9:0.07

10:0.07

11:0.06

Negative Logits

"]=>

-2.36

oppers

-2.21

cest

-2.13

ibaba

-2.10

atown

-2.01

acia

-1.91

"></

-1.86

illance

-1.86

 Parenthood

-1.84

ilda

-1.82

POSITIVE LOGITS

 wiser

2.19

 switch

1.96

 proxies

1.90

 keyboards

1.86

 proxy

1.83

 gloom

1.81

 calibr

1.76

 tilt

1.76

 joystick

1.75

 mechanically

1.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.