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

1:0.10

2:0.07

3:0.07

4:0.07

5:0.07

6:0.08

7:0.09

8:0.08

9:0.09

10:0.08

11:0.07

Negative Logits

Hom

-2.56

enda

-2.49

thood

-2.45

allas

-2.44

ICE

-2.42

AF

-2.36

CF

-2.36

AS

-2.33

ANS

-2.33

 Salt

-2.28

POSITIVE LOGITS

 Rothschild

2.98

 Worm

2.62

Zo

2.59

 bombard

2.56

 Rolls

2.51

rael

2.51

;;;;;;;;;;;;

2.50

Jew

2.48

 attm

2.47

 patented

2.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.