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

0:0.09

1:0.09

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.09

8:0.06

9:0.07

10:0.08

11:0.09

Negative Logits

 Mess

-2.15

��

-2.08

�

-2.06

Rot

-2.01

Aer

-1.96

 millionaires

-1.89

Mot

-1.86

 Roller

-1.80

 Polo

-1.80

 Boat

-1.80

POSITIVE LOGITS

ahime

2.72

aeda

2.50

enhagen

2.32

emale

2.17

aleigh

2.14

abases

2.08

anches

2.06

enium

1.95

irlf

1.93

speech

1.91

Activations Density 0.000%

No Known Activations

This feature has no known activations.