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

0:0.07

1:0.06

2:0.08

3:0.09

4:0.08

5:0.09

6:0.09

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

ocket

-1.82

lege

-1.81

"]=>

-1.64

MIT

-1.61

…)

-1.59

MFT

-1.51

aucus

-1.51

tein

-1.51

 veto

-1.48

.):

-1.48

POSITIVE LOGITS

 reperto

1.76

 makeshift

1.51

 melodies

1.51

 seiz

1.45

 delinqu

1.41

cub

1.40

 menus

1.40

 crews

1.38

ーク

1.38

 prey

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.