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

3:0.09

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.07

11:0.06

Negative Logits

edit

-3.38

units

-3.35

talk

-3.02

Discuss

-2.95

aults

-2.84

comments

-2.84

hang

-2.77

=-=-

-2.74

eatures

-2.72

Characters

-2.71

POSITIVE LOGITS

 Jeanne

3.36

Pav

3.14

 Helm

3.00

bra

2.92

 Devi

2.88

 Pilgrim

2.80

 Patri

2.79

 nipple

2.75

Ruk

2.72

 Christine

2.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.