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

1:0.05

2:0.07

3:0.08

4:0.07

5:0.08

6:0.08

7:0.10

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

entary

-1.84

reditary

-1.73

 Gutenberg

-1.54

stanbul

-1.54

ropolitan

-1.54

 samurai

-1.52

 Enlight

-1.47

 illumination

-1.45

mur

-1.44

版

-1.41

POSITIVE LOGITS

 outper

1.77

atton

1.63

 Courtney

1.56

 contention

1.53

claimed

1.51

 predictably

1.51

alloc

1.51

 routinely

1.48

risk

1.47

 totaled

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.