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

Head Attr Weights

0:0.08

1:0.09

2:0.08

3:0.09

4:0.07

5:0.08

6:0.08

7:0.07

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

maxwell

-3.13

glas

-3.11

pled

-3.10

etsy

-2.91

ichick

-2.82

committee

-2.79

retty

-2.79

hower

-2.73

 secretaries

-2.70

psey

-2.69

POSITIVE LOGITS

 Cycling

3.30

Que

3.12

 Riders

3.04

 Radio

2.91

 Rider

2.85

 Kodi

2.85

 Expression

2.83

 Berserker

2.82

Fur

2.80

 Factor

2.79

Activations Density 0.000%

No Known Activations

This feature has no known activations.