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

2:0.10

3:0.09

4:0.07

5:0.08

6:0.07

7:0.06

8:0.07

9:0.08

10:0.09

11:0.09

Negative Logits

 Colt

-1.76

abase

-1.75

 Columb

-1.61

Production

-1.61

 compet

-1.58

NEC

-1.58

ategic

-1.54

 Rooms

-1.54

competitive

-1.50

physical

-1.50

POSITIVE LOGITS

oğan

1.68

�

1.68

Woman

1.67

 wrap

1.67

 Mara

1.64

 voiced

1.58

 guiActive

1.55

 gays

1.55

 muttered

1.54

 stray

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.