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

0:0.06

1:0.10

2:0.09

3:0.08

4:0.09

5:0.06

6:0.07

7:0.08

8:0.10

9:0.07

10:0.08

11:0.07

Negative Logits

Alz

-2.21

 Bridge

-2.17

ippi

-2.05

 Junction

-2.03

 Metro

-2.02

 Sands

-1.97

 Motors

-1.95

Rex

-1.92

FN

-1.90

 Florence

-1.89

POSITIVE LOGITS

sense

2.53

xual

2.08

 forth

2.03

meal

1.99

 grate

1.95

minist

1.87

 airs

1.81

 envelope

1.79

mercial

1.76

 parcel

1.76

Activations Density 0.000%

No Known Activations

This feature has no known activations.