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

0:0.08

1:0.07

2:0.07

3:0.09

4:0.07

5:0.08

6:0.09

7:0.08

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

Brown

-2.23

 Caldwell

-2.14

 Greene

-2.13

crim

-2.08

roud

-2.01

Redd

-2.01

Eth

-1.99

utenberg

-1.98

 Gibbs

-1.95

erald

-1.95

POSITIVE LOGITS

pmwiki

2.18

さ

2.13

 subsc

1.89

 orbits

1.88

#$

1.83

 surfing

1.81

 measuring

1.81

@#

1.81

 sizing

1.80

ngth

1.80

Activations Density 0.000%

No Known Activations

This feature has no known activations.