INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

1:0.07

2:0.07

3:0.06

4:0.10

5:0.06

6:0.08

7:0.09

8:0.10

9:0.08

10:0.07

11:0.07

Negative Logits

Py

-1.45

itely

-1.38

Ott

-1.32

FUN

-1.32

appa

-1.32

Toy

-1.28

lish

-1.27

-----------

-1.26

NOW

-1.25

️

-1.25

POSITIVE LOGITS

utical

1.77

thood

1.73

nesota

1.67

 contrace

1.63

 resil

1.61

 malaria

1.56

igi

1.52

 perspect

1.52

cffff

1.51

senal

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.