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

0:0.07

1:0.07

2:0.08

3:0.08

4:0.09

5:0.07

6:0.07

7:0.07

8:0.08

9:0.08

10:0.10

11:0.08

Negative Logits

estamp

-2.79

 Subway

-2.64

 Pasadena

-2.60

ummer

-2.58

 mailed

-2.55

 guiName

-2.42

ABE

-2.42

 Marble

-2.41

LOW

-2.38

 Holiday

-2.38

POSITIVE LOGITS

conom

3.42

utsu

3.24

armac

3.10

irit

2.99

rients

2.85

Reloaded

2.80

vati

2.78

ritis

2.72

foundation

2.69

akra

2.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.