INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

1:0.07

2:0.08

3:0.07

4:0.08

5:0.08

6:0.09

7:0.09

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

VID

-2.68

 antennas

-2.60

 サーティワン

-2.57

DN

-2.53

 SOFTWARE

-2.51

 Essential

-2.50

 terminals

-2.49

MSI

-2.48

ITS

-2.43

 Omega

-2.41

POSITIVE LOGITS

 Rebell

2.65

apsed

2.64

 boil

2.61

usher

2.55

 coughing

2.50

rovers

2.48

ewitness

2.45

 whirlwind

2.44

 pneumonia

2.37

 remem

2.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.