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

1:0.09

2:0.08

3:0.07

4:0.08

5:0.07

6:0.07

7:0.08

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

ABE

-2.74

reditary

-2.69

æ

-2.67

 RELE

-2.60

 Borders

-2.59

ean

-2.51

ECB

-2.48

asse

-2.40

tymology

-2.39

Seg

-2.36

POSITIVE LOGITS

 shower

2.72

lav

2.58

 Flask

2.48

 Void

2.42

ickr

2.39

 bang

2.39

utra

2.37

 Potion

2.36

urdue

2.35

 grate

2.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.