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

0:0.07

1:0.08

2:0.08

3:0.07

4:0.07

5:0.08

6:0.09

7:0.07

8:0.08

9:0.08

10:0.09

11:0.07

Negative Logits

ailable

-2.04

eding

-1.91

ellar

-1.88

mington

-1.86

ilings

-1.86

ortium

-1.83

anamo

-1.80

emporary

-1.75

modules

-1.74

chnology

-1.73

POSITIVE LOGITS

 Plane

1.96

 Ride

1.95

 Wage

1.93

 Morse

1.84

 Ratings

1.78

 Twice

1.74

 Init

1.69

 TAMADRA

1.68

 Start

1.66

 Alright

1.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.