INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.08

2:0.08

3:0.07

4:0.09

5:0.08

6:0.08

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

cill

-3.16

 Commissioners

-3.02

 Journals

-2.94

assium

-2.92

 Cheese

-2.82

cker

-2.82

 Gall

-2.81

 Ladies

-2.75

 Hayes

-2.72

kl

-2.68

POSITIVE LOGITS

 shack

3.13

 shaken

2.62

 shatter

2.60

 located

2.58

 traff

2.55

asp

2.53

―

2.48

 transporting

2.46

 dynamically

2.44

 statically

2.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.