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

3:0.07

4:0.09

5:0.08

6:0.09

7:0.09

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

 screenshots

-1.92

 screenshot

-1.76

 documented

-1.65

Pict

-1.59

Vill

-1.59

 spoiler

-1.54

mir

-1.51

 firsthand

-1.51

 swift

-1.50

 headlines

-1.46

POSITIVE LOGITS

 Leilan

2.09

anship

2.06

thood

2.05

oyal

1.82

ilitarian

1.82

ership

1.81

ensable

1.80

ogun

1.80

onement

1.79

ァ

1.77

Activations Density 0.000%

No Known Activations

This feature has no known activations.