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

0:0.08

1:0.11

2:0.08

3:0.08

4:0.08

5:0.06

6:0.08

7:0.07

8:0.08

9:0.06

10:0.09

11:0.06

Negative Logits

akespe

-1.76

�醒

-1.69

guyen

-1.54

 FILE

-1.54

FIL

-1.51

..............

-1.50

pic

-1.50

 Handler

-1.49

gettable

-1.49

aml

-1.47

POSITIVE LOGITS

 lockout

1.73

 newsletters

1.58

 Keynes

1.58

 organised

1.56

 casinos

1.54

 earthquakes

1.51

 signings

1.48

 sclerosis

1.47

 robberies

1.46

ements

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.