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

0:0.08

1:0.05

2:0.09

3:0.09

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

 shutter

-1.81

 curtains

-1.76

 griev

-1.76

gou

-1.75

 Repeat

-1.69

 repair

-1.67

 conservation

-1.66

 counters

-1.62

 Altern

-1.60

 carriage

-1.55

POSITIVE LOGITS

comings

2.06

orld

2.04

icter

1.91

>)

1.91

rice

1.87

angular

1.85

iated

1.83

buquerque

1.83

starter

1.80

 Lumpur

1.79

Activations Density 0.000%

No Known Activations

This feature has no known activations.