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

0:0.07

1:0.08

2:0.08

3:0.11

4:0.08

5:0.07

6:0.08

7:0.07

8:0.07

9:0.07

10:0.09

11:0.06

Negative Logits

SX

-2.56

 follow

-2.44

 Virtue

-2.39

Ou

-2.35

 Equity

-2.32

Coy

-2.31

 outset

-2.23

 Manifest

-2.21

 unsurprisingly

-2.21

 Pers

-2.11

POSITIVE LOGITS

missing

3.39

�

2.89

ctrl

2.77

 rotting

2.65

rimp

2.60

Frag

2.44

buf

2.42

Flight

2.41

finger

2.39

osta

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.