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

1:0.06

2:0.08

3:0.08

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

 rall

-1.78

 classics

-1.52

�

-1.48

 Zombies

-1.45

 scholar

-1.42

 Classics

-1.41

rawdownloadcloneembedreportprint

-1.39

OPLE

-1.38

 downt

-1.34

odox

-1.33

POSITIVE LOGITS

aniel

1.47

phrine

1.46

ilk

1.41

Pak

1.39

bis

1.38

ulus

1.38

address

1.36

 subsidiary

1.33

bach

1.33

ama

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.