INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

1:0.07

2:0.07

3:0.07

4:0.08

5:0.09

6:0.09

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 Shame

-2.29

dylib

-2.15

 Colour

-2.12

 uproar

-2.11

 ageing

-2.07

 blight

-2.07

 Hello

-2.02

 unhappy

-2.01

)?

-1.99

 billed

-1.99

POSITIVE LOGITS

ezvous

2.49

umbn

2.39

aido

2.22

earchers

2.21

anch

2.19

aco

2.16

zhou

2.11

inse

2.11

onto

2.10

anke

2.10

Activations Density 0.000%

No Known Activations

This feature has no known activations.