INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

4:0.07

5:0.08

6:0.07

7:0.09

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

dra

-2.71

bern

-2.70

estamp

-2.67

"},

-2.67

 Sagan

-2.56

 Stern

-2.55

malink

-2.54

dq

-2.49

 Wheeler

-2.49

 Nerd

-2.48

POSITIVE LOGITS

hiba

2.58

relation

2.55

ベ

2.53

lamm

2.38

�

2.34

 integ

2.34

��

2.34

 conclud

2.30

 multiplying

2.30

 interoper

2.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.