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

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

 Born

-1.98

 Photographer

-1.74

 Revis

-1.70

 Omega

-1.68

 reboot

-1.66

 Burnett

-1.60

 circulated

-1.59

 Ramirez

-1.59

 Motors

-1.56

 Vide

-1.56

POSITIVE LOGITS

iasm

2.23

ances

2.08

ancies

2.05

)*

1.91

nces

1.90

gae

1.86

rament

1.81

 sqor

1.79

 advoc

1.78

 proble

1.77

Activations Density 0.000%

No Known Activations

This feature has no known activations.