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

0:0.09

1:0.11

2:0.10

3:0.07

4:0.06

5:0.11

6:0.06

7:0.04

8:0.12

9:0.05

10:0.06

11:0.08

Negative Logits

azines

-1.68

ships

-1.61

tons

-1.59

 ceilings

-1.58

 arrivals

-1.56

 Leilan

-1.50

 bedrooms

-1.49

Known

-1.49

 politic

-1.47

runners

-1.47

POSITIVE LOGITS

ivan

1.72

ographer

1.60

 Maid

1.51

):

1.46

alks

1.46

Wan

1.44

):

1.44

 eleph

1.43

Guy

1.43

�

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.