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

1:0.08

2:0.08

3:0.08

4:0.09

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

owler

-1.70

alon

-1.50

ior

-1.49

>)

-1.49

taboola

-1.47

itri

-1.40

ively

-1.39

.")

-1.39

=>

-1.38

SEE

-1.37

POSITIVE LOGITS

 bandwagon

1.68

���

1.62

zon

1.58

�

1.55

 constitu

1.55

 dime

1.54

 Genocide

1.53

 tribe

1.51

zag

1.50

 gamble

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.