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

2:0.06

3:0.09

4:0.08

5:0.08

6:0.07

7:0.09

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

 irresistible

-2.34

 Flav

-2.23

 Prospect

-2.21

 Lever

-2.19

 Fold

-2.19

 Grape

-2.17

 Meet

-2.13

 Negro

-2.09

 Gorge

-2.09

 Yosemite

-2.09

POSITIVE LOGITS

maxwell

2.98

hene

2.66

hovah

2.53

getic

2.49

onse

2.48

anamo

2.47

 Leilan

2.46

achine

2.44

ema

2.41

cha

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.