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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

 Kabul

-2.96

KGB

-2.92

Putin

-2.85

 Ottoman

-2.85

 Alps

-2.84

ski

-2.83

ITV

-2.75

 Austria

-2.69

 Maced

-2.63

 Pesh

-2.60

POSITIVE LOGITS

rely

3.13

 Clover

2.62

enture

2.59

 Quit

2.56

recy

2.56

ependence

2.46

CHO

2.45

pmwiki

2.43

RET

2.43

oresc

2.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.