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

3:0.07

4:0.08

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

 Bruno

-2.57

lag

-2.54

CF

-2.51

Fen

-2.50

 Cuba

-2.48

 IMAGES

-2.47

 Carib

-2.46

 Dublin

-2.41

 Castro

-2.40

 REUTERS

-2.36

POSITIVE LOGITS

 subpoena

2.79

multipl

2.52

 encode

2.36

 mortg

2.36

"]=>

2.35

UTF

2.35

 democrat

2.34

 decode

2.31

achment

2.30

gom

2.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.