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

0:0.06

1:0.08

2:0.09

3:0.08

4:0.08

5:0.07

6:0.09

7:0.07

8:0.07

9:0.07

10:0.10

11:0.09

Negative Logits

 trademarks

-1.43

breakers

-1.42

*/

-1.40

ronics

-1.38

zza

-1.37

illery

-1.36

wine

-1.36

 Moves

-1.35

 logo

-1.35

buster

-1.32

POSITIVE LOGITS

isode

1.97

izabeth

1.74

etheus

1.69

pmwiki

1.66

flix

1.66

 millenn

1.66

entimes

1.64

zsche

1.64

bilt

1.61

 unbeliev

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.