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

0:0.08

1:0.07

2:0.08

3:0.07

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

forth

-1.61

itar

-1.52

enne

-1.52

ascript

-1.51

eus

-1.45

rw

-1.44

』

-1.43

*.

-1.42

 accessed

-1.41

POSITIVE LOGITS

)=(

1.65

BTC

1.62

��

1.57

sonian

1.52

Vote

1.45

..............

1.45

ALSE

1.43

 contradiction

1.42

 srfAttach

1.38

ancel

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.