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

0:0.07

1:0.11

2:0.08

3:0.08

4:0.07

5:0.09

6:0.06

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

glers

-1.72

 anonymously

-1.60

 misconduct

-1.57

 alive

-1.51

Leaks

-1.45

 hospitalized

-1.44

 nominated

-1.43

 inflic

-1.41

 imperson

-1.41

 purportedly

-1.38

POSITIVE LOGITS

meal

1.88

paralle

1.71

OX

1.66

Ja

1.54

龍喚士

1.54

Nit

1.54

Ale

1.52

Ire

1.50

FUL

1.49

ilst

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.