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

0:0.08

1:0.08

2:0.07

3:0.09

4:0.07

5:0.08

6:0.09

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

Wag

-2.98

reply

-2.75

 announcements

-2.67

 confir

-2.65

 briefings

-2.63

 Donation

-2.60

 endorsements

-2.52

 McCoy

-2.52

 prophe

-2.48

 Speak

-2.41

POSITIVE LOGITS

rent

2.99

oided

2.67

Weak

2.63

 Mikhail

2.61

alty

2.57

 virginity

2.55

ِ

2.54

unin

2.54

َ

2.53

 Petr

2.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.