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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.11

1:0.08

2:0.09

3:0.06

4:0.06

5:0.10

6:0.12

7:0.05

8:0.07

9:0.08

10:0.06

11:0.07

Negative Logits

assad

-1.94

-1.81

�

-1.79

XL

-1.67

OE

-1.61

-1.51

FY

-1.51

SPONSORED

-1.50

VB

-1.50

-1.49

POSITIVE LOGITS

 vigilant

1.43

 furious

1.42

EStreamFrame

1.41

 rooting

1.41

wat

1.39

Pwr

1.36

 Dying

1.35

 endure

1.34

 vigilante

1.33

 coma

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.