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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

ngth

-2.30

packing

-2.07

maps

-1.81

ppings

-1.77

urgy

-1.66

required

-1.62

selage

-1.60

istries

-1.57

thood

-1.56

func

-1.55

POSITIVE LOGITS

 unfair

1.68

 false

1.60

 discriminating

1.57

 swing

1.53

 sway

1.52

azo

1.50

 spurious

1.48

 prejud

1.48

 fraudulent

1.47

 favourable

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.