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

1:0.07

2:0.07

3:0.08

4:0.07

5:0.09

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

RESULTS

-1.36

◼

-1.33

itatively

-1.30

MET

-1.26

***

-1.25

 Illum

-1.25

 Seymour

-1.25

●

-1.22

[(

-1.22

 quant

-1.21

POSITIVE LOGITS

ゴン

1.72

amba

1.71

 warr

1.64

aho

1.51

legate

1.48

 belts

1.47

emale

1.44

clair

1.42

yip

1.41

jon

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.