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

0:0.08

1:0.06

2:0.09

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

angered

-2.13

spir

-1.65

animous

-1.64

!'

-1.53

brate

-1.52

edi

-1.49

 limb

-1.48

coh

-1.44

agle

-1.38

yr

-1.38

POSITIVE LOGITS

 Conquest

1.47

renheit

1.34

 included

1.34

ories

1.31

 upgr

1.28

 matches

1.27

 suites

1.26

ription

1.26

 Utilities

1.22

comings

1.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.