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

1:0.11

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.06

8:0.08

9:0.09

10:0.07

11:0.07

Negative Logits

 Downs

-1.93

Pin

-1.69

 Torch

-1.59

Nev

-1.58

CPC

-1.52

.","

-1.50

Rio

-1.49

plan

-1.44

GHz

-1.43

 Ground

-1.43

POSITIVE LOGITS

mble

2.36

osuke

2.03

OME

2.02

ASED

1.96

OSE

1.90

athy

1.83

ipel

1.77

umbn

1.73

Adams

1.71

sei

1.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.