INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

3:0.09

4:0.08

5:0.08

6:0.09

7:0.06

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 aven

-2.73

 Siber

-2.67

ascript

-2.67

Wem

-2.64

 poisons

-2.49

doc

-2.46

ngth

-2.45

terday

-2.44

CPR

-2.42

 antioxid

-2.39

POSITIVE LOGITS

RTX

3.08

 Rent

2.92

NX

2.90

 Atlas

2.52

actionDate

2.50

 Reserved

2.49

escent

2.49

 Seraph

2.49

 Galaxy

2.48

 peaked

2.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.