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

Head Attr Weights

0:0.09

1:0.08

2:0.08

3:0.06

4:0.07

5:0.08

6:0.09

7:0.09

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

 marrow

-1.93

 Oval

-1.72

idge

-1.71

 shelves

-1.71

>[

-1.69

 veins

-1.69

 sink

-1.69

DOI

-1.68

idges

-1.65

 slides

-1.65

POSITIVE LOGITS

 Franch

2.05

 Volunte

2.03

practice

1.94

Dak

1.92

��

1.92

ASA

1.82

enfranch

1.82

advert

1.80

reprene

1.80

ammy

1.76

Activations Density 0.000%

No Known Activations

This feature has no known activations.