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

0:0.09

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

ヘラ

-1.67

Picture

-1.59

adapt

-1.54

 Carbuncle

-1.53

cellent

-1.51

 Incarnation

-1.51

Unique

-1.48

irin

-1.48

emort

-1.47

Result

-1.47

POSITIVE LOGITS

entimes

1.59

ikan

1.57

idal

1.57

ionage

1.54

urion

1.54

sterdam

1.50

ritz

1.50

 studios

1.46

gian

1.45

estic

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.