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

1:0.08

2:0.07

3:0.08

4:0.07

5:0.09

6:0.08

7:0.07

8:0.09

9:0.09

10:0.08

11:0.08

Negative Logits

Dat

-2.94

jj

-2.68

Sov

-2.65

š

-2.60

RT

-2.53

 retarded

-2.51

Dyn

-2.50

Qin

-2.45

ador

-2.45

 Jiang

-2.44

POSITIVE LOGITS

 Mercer

3.01

anca

2.75

ascript

2.69

 Hers

2.52

achus

2.51

 Cobb

2.51

 Gret

2.45

 Elys

2.43

 Beverly

2.43

 Charlotte

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.