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

2:0.09

3:0.08

4:0.07

5:0.09

6:0.06

7:0.09

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

ウス

-2.96

utenberg

-2.96

DNA

-2.83

cum

-2.64

;;;;;;;;;;;;

-2.62

coat

-2.61

ERA

-2.60

 サーティワン

-2.55

Cum

-2.47

 Bauer

-2.46

POSITIVE LOGITS

USS

2.77

voy

2.40

 droid

2.40

 spotlight

2.39

 Rodrigo

2.36

yout

2.36

intent

2.35

pil

2.35

tesy

2.34

outheast

2.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.