INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.07

2:0.08

3:0.08

4:0.07

5:0.08

6:0.09

7:0.06

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

onite

-1.49

 brakes

-1.38

 Unic

-1.33

 pads

-1.33

GP

-1.33

 Tags

-1.33

 blocker

-1.30

toe

-1.29

 stem

-1.29

 goggles

-1.28

POSITIVE LOGITS

��

1.87

successful

1.83

]"

1.66

]."

1.59

�

1.59

conduct

1.55

.]

1.53

]).

1.50

ournal

1.49

�

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.