INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

3:0.09

4:0.09

5:0.08

6:0.07

7:0.08

8:0.09

9:0.07

10:0.07

11:0.08

Negative Logits

 laun

-1.68

 perpet

-1.50

 retrieval

-1.48

 unwitting

-1.46

 discredit

-1.44

 Krypt

-1.41

 Chandra

-1.39

 occasion

-1.39

 Trojan

-1.36

Zup

-1.36

POSITIVE LOGITS

Shape

1.85

docs

1.79

-[

1.75

tyard

1.69

itled

1.64

CENT

1.63

[+

1.63

�

1.62

ancies

1.61

��

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.