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

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.09

9:0.07

10:0.09

11:0.08

Negative Logits

Jews

-1.46

 Cinema

-1.45

"'

-1.45

 Hindus

-1.43

 Movie

-1.42

np

-1.41

 Playing

-1.41

 Pigs

-1.41

agall

-1.40

 dishon

-1.39

POSITIVE LOGITS

omics

2.02

chart

1.91

 ranges

1.77

PDATE

1.70

 charts

1.70

lander

1.69

pub

1.67

omsday

1.67

meter

1.64

ngth

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.