INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.07

4:0.09

5:0.07

6:0.08

7:0.08

8:0.07

9:0.09

10:0.08

11:0.09

Negative Logits

 Paradise

-1.32

 Casino

-1.25

 Stage

-1.23

 ballet

-1.23

 Secondary

-1.19

 reservoir

-1.17

 Nirvana

-1.16

 barg

-1.15

 chess

-1.14

castle

-1.14

POSITIVE LOGITS

�

1.53

 Cosponsors

1.51

icia

1.48

 millenn

1.47

TERN

1.46

ircraft

1.40

RIC

1.39

ANCE

1.38

ahoo

1.36

PDATE

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.