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

3:0.07

4:0.07

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

DI

-3.02

aples

-2.76

Git

-2.60

Termin

-2.58

 Guantanamo

-2.54

 Pillar

-2.52

Tip

-2.50

Optional

-2.46

 Brune

-2.41

Recommended

-2.40

POSITIVE LOGITS

coh

3.32

 enthusi

2.83

ersive

2.82

 acknow

2.81

 costume

2.79

 advertis

2.79

 domest

2.79

 melanch

2.75

 stag

2.74

pse

2.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.