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

1:0.09

2:0.07

3:0.09

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.09

Negative Logits

kh

-1.70

Obi

-1.68

 guarant

-1.62

�

-1.55

coc

-1.50

KL

-1.48

unal

-1.47

cos

-1.47

 anat

-1.45

Nay

-1.45

POSITIVE LOGITS

 Affect

1.73

etheless

1.71

essim

1.69

 msec

1.58

udge

1.54

 Doomsday

1.54

upt

1.52

schild

1.51

ocket

1.50

RESULTS

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.