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

1:0.09

2:0.07

3:0.08

4:0.07

5:0.08

6:0.10

7:0.07

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

dyn

-3.21

 machinery

-2.96

 Diesel

-2.80

 fasc

-2.71

 worldwide

-2.65

 indisp

-2.65

 millenn

-2.64

 strut

-2.63

 fluor

-2.58

 diesel

-2.56

POSITIVE LOGITS

reb

3.05

ayne

2.98

ubis

2.95

cheon

2.89

SCP

2.84

iasis

2.80

ciation

2.78

arde

2.70

Chan

2.63

inged

2.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.