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

0:0.07

1:0.05

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.10

9:0.09

10:0.08

11:0.09

Negative Logits

 Desmond

-1.58

 motorcycles

-1.55

‎

-1.53

 footsteps

-1.52

atonin

-1.47

 casualty

-1.45

\'

-1.44

 Krishna

-1.43

 Sergei

-1.43

 motorcycle

-1.42

POSITIVE LOGITS

atown

1.81

hub

1.78

umblr

1.70

��

1.70

Hub

1.61

indust

1.59

arte

1.57

enfranch

1.54

consumer

1.51

plete

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.