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

0:0.07

1:0.07

2:0.07

3:0.09

4:0.07

5:0.08

6:0.11

7:0.10

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

Lev

-1.56

raphics

-1.51

%]

-1.51

shock

-1.50

 succeeding

-1.47

 Levant

-1.44

utz

-1.43

KH

-1.42

aneously

-1.41

foe

-1.39

POSITIVE LOGITS

$$

1.69

ˈ

1.65

═

1.65

 interchange

1.63

 commandments

1.62

 Restaur

1.61

orest

1.60

Lago

1.59

ecause

1.58

 deduction

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.