INDEX

Explanations

statements related to personal relationships and transitions in political or workplace contexts

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

0:0.11

1:0.26

2:0.09

3:0.04

4:0.03

5:0.03

6:0.13

7:0.05

8:0.02

9:0.04

10:0.09

11:0.04

Negative Logits

 Shroud

-3.24

reen

-3.06

ombat

-2.98

acter

-2.92

 sans

-2.89

り

-2.88

Browser

-2.78

 stra

-2.76

ijn

-2.73

ppings

-2.73

POSITIVE LOGITS

 Corey

9.07

Core

5.41

 Core

4.31

 Carey

3.67

 Cory

3.62

Anth

3.59

 core

3.42

core

3.42

 Britt

3.20

 Wyatt

3.19

Activations Density 0.004%

statements related to personal relationships and transitions in political or workplace contexts

No Known Activations