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

1:0.06

2:0.08

3:0.08

4:0.09

5:0.09

6:0.09

7:0.09

8:0.09

9:0.07

10:0.07

11:0.08

Negative Logits

awaru

-2.02

 Recover

-1.70

vation

-1.68

 Convert

-1.66

Suddenly

-1.66

Higher

-1.63

geist

-1.61

 Moonlight

-1.61

¶

-1.59

 Stevenson

-1.58

POSITIVE LOGITS

actionDate

1.90

 labels

1.85

modules

1.83

oys

1.81

 mortar

1.81

afety

1.78

yrics

1.77

inks

1.76

iable

1.72

iol

1.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.