INDEX

Explanations

grammatical elements and punctuation in the text

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.06

1:0.03

2:0.07

3:0.14

4:0.09

5:0.06

6:0.05

7:0.09

8:0.09

9:0.06

10:0.06

11:0.14

Negative Logits

Thumbnail

-2.41

oliath

-2.21

 Judaism

-2.19

unky

-2.15

TPPStreamerBot

-2.06

 psychologically

-2.04

מ

-2.02

 flawed

-1.97

生

-1.97

 neuroscience

-1.97

POSITIVE LOGITS

 arri

3.22

�

3.03

ll

2.85

 Colo

2.83

 tion

2.76

Mex

2.72

 COUNTY

2.67

ornia

2.64

 elig

2.62

 Paso

2.58

Activations Density 0.000%

grammatical elements and punctuation in the text

No Known Activations