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

1:0.07

2:0.08

3:0.08

4:0.07

5:0.06

6:0.10

7:0.08

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

 Sergey

-1.85

 Aram

-1.74

 Sergei

-1.62

-1.54

 address

-1.53

ipal

-1.50

son

-1.48

 Mazda

-1.48

 Tata

-1.48

ラン

-1.48

POSITIVE LOGITS

pmwiki

1.82

exper

1.77

eeds

1.75

angled

1.71

nw

1.67

 Witches

1.66

ocaust

1.60

eming

1.60

iotics

1.56

wart

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.