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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.07

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

 healer

-1.44

 cape

-1.43

 jets

-1.36

 fame

-1.30

jet

-1.29

Applications

-1.27

fold

-1.26

 fragments

-1.24

 inflamm

-1.23

 Courier

-1.23

POSITIVE LOGITS

livious

1.80

�

1.70

��

1.67

�

1.65

�醒

1.65

unn

1.61

amacare

1.48

olicited

1.45

�

1.44

ˈ

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.