INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

1:0.10

2:0.09

3:0.09

4:0.08

5:0.07

6:0.07

7:0.07

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

ements

-1.83

Legend

-1.81

Appearances

-1.71

letters

-1.69

Marvel

-1.68

 captivity

-1.64

 Illum

-1.63

 Conquer

-1.63

odon

-1.57

omics

-1.55

POSITIVE LOGITS

achev

1.71

acebook

1.61

 Eston

1.58

osph

1.55

ataka

1.54

 perce

1.54

oğ

1.52

ğ

1.52

 contrasted

1.49

 dispatcher

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.