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

0:0.06

1:0.05

2:0.08

3:0.07

4:0.09

5:0.08

6:0.08

7:0.12

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 persecuted

-1.70

 Nation

-1.61

nation

-1.48

 Armageddon

-1.44

 assassination

-1.41

 assassinate

-1.40

 Maher

-1.39

ipedia

-1.38

emia

-1.37

 launch

-1.37

POSITIVE LOGITS

etsy

1.64

optional

1.61

YR

1.60

�

1.57

xt

1.55

dylib

1.55

rentices

1.55

DIT

1.52

Lic

1.48

Grad

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.