INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.09

2:0.09

3:0.08

4:0.06

5:0.07

6:0.09

7:0.07

8:0.09

9:0.08

10:0.07

11:0.07

Negative Logits

notations

-1.82

intent

-1.79

onyms

-1.76

terms

-1.69

styles

-1.55

vern

-1.51

activity

-1.49

fml

-1.49

oji

-1.47

orks

-1.47

POSITIVE LOGITS

DAQ

1.53

LLP

1.48

 Bridgewater

1.47

Khe

1.46

 thee

1.45

 Hoover

1.41

ERO

1.41

Ka

1.38

 shareholder

1.36

 headquartered

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.