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

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.09

9:0.08

10:0.09

11:0.09

Negative Logits

 blat

-2.33

 wiser

-2.05

 preach

-1.89

 mishand

-1.88

 revolving

-1.86

 swoop

-1.86

-+-+

-1.85

uten

-1.85

 downside

-1.83

 awhile

-1.81

POSITIVE LOGITS

 Identification

2.28

 Regist

2.18

 Surv

2.15

 Documents

2.05

 Document

2.02

Di

2.00

 Publication

1.97

recogn

1.97

Sym

1.94

vern

1.93

Activations Density 0.000%

No Known Activations

This feature has no known activations.