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

1:0.05

2:0.10

3:0.08

4:0.07

5:0.07

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

ּ

-1.74

#$

-1.65

ochond

-1.62

 outweigh

-1.53

 mouth

-1.53

mp

-1.52

 kindred

-1.50

 mischief

-1.48

beg

-1.48

 bastard

-1.46

POSITIVE LOGITS

urations

2.21

urated

2.02

handled

1.96

awei

1.95

spr

1.85

classified

1.81

order

1.79

ships

1.76

rend

1.70

Delivery

1.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.