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

0:0.07

1:0.07

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.07

8:0.10

9:0.08

10:0.07

11:0.08

Negative Logits

 Invalid

-1.99

 Possible

-1.68

 Symbol

-1.63

Quantity

-1.58

"/>

-1.56

Fax

-1.51

zin

-1.48

 Number

-1.46

 aloud

-1.44

 TODAY

-1.44

POSITIVE LOGITS

��極

1.75

田

1.60

 runners

1.58

��

1.57

��

1.54

FS

1.53

��

1.53

esm

1.52

JR

1.51

ーティ

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.