INDEX

Explanations

No Explanations Found

New Auto-Interp

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

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.07

4:0.08

5:0.09

6:0.07

7:0.08

8:0.07

9:0.08

10:0.09

11:0.09

Negative Logits

umbn

-1.91

itus

-1.61

 unbeliev

-1.60

 Scientology

-1.58

 Abrams

-1.57

anmar

-1.49

apter

-1.48

Nau

-1.45

awei

-1.44

 Pavel

-1.43

POSITIVE LOGITS

 faire

1.57

 menstrual

1.50

 stitches

1.45

bom

1.42

者

1.41

iers

1.39

 administering

1.37

emen

1.36

 stitch

1.32

aird

1.32

Activations Density 0.000%

No Known Activations

This feature has no known activations.