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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.09

3:0.08

4:0.06

5:0.08

6:0.07

7:0.07

8:0.09

9:0.07

10:0.07

11:0.09

Negative Logits

 scanner

-3.36

 censor

-2.93

 blacklist

-2.75

 google

-2.63

DM

-2.57

BBC

-2.57

 Wired

-2.56

 spinach

-2.54

 util

-2.53

amp

-2.52

POSITIVE LOGITS

�

3.34

�

3.14

�

3.14

ouver

3.01

Mos

2.99

��

2.90

marriage

2.88

asonry

2.88

MQ

2.83

�

2.82

Activations Density 0.000%

No Known Activations

This feature has no known activations.