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

0:0.07

1:0.05

2:0.09

3:0.09

4:0.08

5:0.09

6:0.09

7:0.09

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

ulus

-1.51

 clause

-1.47

 tariffs

-1.47

 rebate

-1.43

 saliva

-1.37

 Clause

-1.35

BuyableInstoreAndOnline

-1.35

 coupons

-1.35

 sack

-1.31

gements

-1.31

POSITIVE LOGITS

christ

1.75

 conver

1.72

 travers

1.69

 programmers

1.55

 altern

1.51

 upgr

1.49

omething

1.45

DEP

1.45

hend

1.41

 functionally

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.