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

0:0.08

1:0.05

2:0.09

3:0.07

4:0.09

5:0.08

6:0.08

7:0.09

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 commissions

-1.76

inav

-1.73

isse

-1.73

 purse

-1.71

 invis

-1.68

bye

-1.63

 commission

-1.62

 congratulations

-1.61

 Nielsen

-1.58

 mids

-1.56

POSITIVE LOGITS

osite

2.10

angular

2.08

rio

1.94

 Features

1.75

ould

1.68

 Related

1.65

®

1.64

 Requires

1.62

iated

1.58

 Component

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.