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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.09

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.06

10:0.08

11:0.09

Negative Logits

 Laure

-1.83

 Sisters

-1.76

 Berger

-1.63

Oak

-1.62

 Vander

-1.62

 Univ

-1.59

 Bian

-1.58

 Argent

-1.58

 underdog

-1.56

DeL

-1.55

POSITIVE LOGITS

 captcha

1.98

agus

1.83

 cess

1.81

 compulsion

1.72

lihood

1.69

enge

1.68

 conflic

1.67

 coercive

1.62

duction

1.62

+)

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.