INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.07

3:0.08

4:0.06

5:0.10

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

icter

-3.19

 respir

-3.15

byss

-2.88

Sym

-2.77

Layer

-2.67

Animation

-2.59

 ILCS

-2.57

 cylinders

-2.51

ETF

-2.49

Frag

-2.47

POSITIVE LOGITS

STA

2.51

ryn

2.50

Cra

2.38

 Chatt

2.31

 invitations

2.29

BDS

2.28

Che

2.27

ogyn

2.25

ogo

2.23

 Sussex

2.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.