INDEX

Explanations

No Explanations Found

New Auto-Interp

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

3:0.09

4:0.09

5:0.08

6:0.09

7:0.06

8:0.06

9:0.10

10:0.07

11:0.08

Negative Logits

Oo

-1.62

potion

-1.58

PID

-1.47

 Radius

-1.45

 Patty

-1.43

 nerds

-1.42

 Juice

-1.42

please

-1.41

 Crack

-1.40

mercial

-1.38

POSITIVE LOGITS

vier

1.62

anca

1.61

ッド

1.49

ONT

1.49

orld

1.48

��

1.45

ティ

1.43

1.40

sem

1.38

EGA

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.