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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.04

1:0.04

2:0.15

3:0.10

4:0.06

5:0.04

6:0.12

7:0.16

8:0.04

9:0.04

10:0.10

11:0.07

Negative Logits

 hoops

-1.57

angelo

-1.54

ighters

-1.49

bud

-1.48

 gears

-1.48

 trickle

-1.47

 inquire

-1.47

 decide

-1.39

mur

-1.38

ettle

-1.38

POSITIVE LOGITS

ailability

2.07

 サーティワン

1.85

 Azerb

1.83

amation

1.82

��

1.82

��極

1.73

ortunate

1.66

 comr

1.61

��

1.59

\\\\\\\\

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.