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

0:0.09

1:0.10

2:0.07

3:0.07

4:0.07

5:0.08

6:0.09

7:0.07

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

turned

-1.80

Textures

-1.69

opped

-1.65

claimed

-1.65

vantage

-1.63

ended

-1.61

rived

-1.60

liner

-1.59

pressed

-1.56

xes

-1.54

POSITIVE LOGITS

Dru

1.67

 mell

1.48

 accomplishments

1.46

Obj

1.46

maj

1.46

 Antar

1.41

 bount

1.41

Kab

1.41

 easing

1.39

Aid

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.