INDEX

Explanations

punctuation marks and the structure of sentences

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.17

1:0.11

2:0.11

3:0.04

4:0.05

5:0.03

6:0.05

7:0.09

8:0.03

9:0.04

10:0.17

11:0.06

Negative Logits

adal

-3.24

REL

-2.99

Harris

-2.98

CVE

-2.83

paio

-2.83

tackle

-2.77

RAD

-2.76

DD

-2.72

 Moff

-2.66

CAL

-2.65

POSITIVE LOGITS

Vit

9.31

vit

5.50

 Blend

4.61

 blender

4.34

 Vita

3.72

Vor

3.69

 vitamins

3.64

Wit

3.64

vas

3.53

Nit

3.53

Activations Density 0.000%

punctuation marks and the structure of sentences

No Known Activations