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

1:0.08

2:0.08

3:0.07

4:0.09

5:0.08

6:0.08

7:0.09

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

epad

-1.59

 Conce

-1.56

intent

-1.56

arij

-1.53

 Citation

-1.53

isma

-1.53

 Regulations

-1.52

illac

-1.51

skirts

-1.50

icut

-1.49

POSITIVE LOGITS

IBLE

1.62

1.59

 Emmy

1.59

 suck

1.58

 tantal

1.57

 juicy

1.56

 sucker

1.54

 tremend

1.51

 listener

1.51

ensitive

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.