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

3:0.08

4:0.08

5:0.08

6:0.09

7:0.08

8:0.08

9:0.08

10:0.09

11:0.07

Negative Logits

idable

-1.86

eland

-1.75

 Detention

-1.53

 compr

-1.52

 Hilton

-1.49

龍

-1.46

 critic

-1.44

);

-1.44

��

-1.43

 Identity

-1.42

POSITIVE LOGITS

sheets

1.68

bernatorial

1.68

cohol

1.67

esters

1.64

 frying

1.56

tein

1.54

scenes

1.52

nes

1.51

 Volunte

1.51

oaded

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.