INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.09

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.09

8:0.08

9:0.07

10:0.06

11:0.10

Negative Logits

 Monthly

-1.70

 Ratings

-1.64

Performance

-1.48

 endurance

-1.48

 Rated

-1.42

 Weekly

-1.42

ETF

-1.42

Technical

-1.41

 Trials

-1.39

POSITIVE LOGITS

ell

1.71

aryl

1.64

schild

1.63

 curly

1.55

emphasis

1.52

instead

1.52

ukong

1.51

oof

1.50

 unmarked

1.49

 shorth

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.