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

1:0.16

2:0.07

3:0.08

4:0.07

5:0.08

6:0.08

7:0.06

8:0.07

9:0.06

10:0.06

11:0.07

Negative Logits

 Epstein

-1.65

enda

-1.59

 Material

-1.58

 Ibid

-1.57

 Operation

-1.56

 Organization

-1.53

 Construction

-1.52

 Letters

-1.51

 Stadium

-1.49

 Guns

-1.49

POSITIVE LOGITS

oult

2.23

mble

2.04

yip

1.98

kef

1.85

ugu

1.84

xtap

1.84

porary

1.82

 certify

1.81

plet

1.77

xual

1.77

Activations Density 0.000%

No Known Activations

This feature has no known activations.