INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.08

4:0.06

5:0.08

6:0.10

7:0.08

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

 Circuit

-3.25

 Built

-3.08

Flo

-2.93

AIR

-2.77

 Architect

-2.65

Oxy

-2.61

PK

-2.60

 Remastered

-2.54

GPS

-2.54

 Puzzle

-2.54

POSITIVE LOGITS

doms

3.35

ifax

2.96

wives

2.91

ourgeois

2.78

 welf

2.75

 dism

2.75

 grievance

2.72

iatus

2.71

 raiding

2.70

 overdoses

2.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.