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

0:0.08

1:0.05

2:0.08

3:0.08

4:0.09

5:0.08

6:0.09

7:0.09

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

owship

-1.78

cult

-1.78

hov

-1.73

 spirits

-1.69

tur

-1.65

casts

-1.65

 Bulg

-1.59

utic

-1.58

cast

-1.56

 Concent

-1.55

POSITIVE LOGITS

AMA

1.91

 clipboard

1.79

Vote

1.59

ede

1.56

FAA

1.53

 Kenyan

1.52

 biased

1.51

 biom

1.49

 polling

1.47

USD

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.