INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.07

4:0.09

5:0.07

6:0.07

7:0.08

8:0.07

9:0.07

10:0.09

11:0.07

Negative Logits

 offending

-1.53

 peripheral

-1.49

 predetermined

-1.49

 specific

-1.48

 conditional

-1.46

 tagging

-1.44

 appropriation

-1.42

 mismatch

-1.40

 intent

-1.39

 unrelated

-1.37

POSITIVE LOGITS

aug

1.78

apeake

1.77

DragonMagazine

1.76

 Franch

1.70

estern

1.66

姫

1.61

spir

1.60

cephal

1.56

illin

1.56

terday

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.