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

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

enez

-2.61

APTER

-2.60

ubis

-2.47

�

-2.26

)))

-2.25

Lu

-2.25

ensed

-2.22

angible

-2.20

sa

-2.17

___

-2.16

POSITIVE LOGITS

 Norton

2.70

 Frankie

2.60

dot

2.50

 Jury

2.44

 Tomorrow

2.43

 Caucas

2.42

odon

2.41

 Fnatic

2.38

 neocons

2.38

 negro

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.