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

1:0.05

2:0.08

3:0.08

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

ridor

-1.87

ase

-1.69

yden

-1.69

ildo

-1.64

Sat

-1.62

emi

-1.58

idon

-1.55

nell

-1.55

Romney

-1.52

Allah

-1.52

POSITIVE LOGITS

 Emblem

1.78

 Attributes

1.74

 Agric

1.59

ré

1.57

 Tact

1.57

 Strongh

1.56

 Templar

1.53

 playbook

1.51

 Practices

1.49

 Compass

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.