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

1:0.07

2:0.08

3:0.08

4:0.09

5:0.07

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

ibu

-2.95

seless

-2.92

 feds

-2.91

ンジ

-2.87

icut

-2.83

antine

-2.77

entanyl

-2.74

illac

-2.72

版

-2.71

quished

-2.67

POSITIVE LOGITS

 Moff

3.33

 Shepherd

2.68

 analys

2.68

 programme

2.60

 summar

2.58

 Luther

2.57

Ips

2.52

 Levi

2.51

 Bolton

2.50

 Giles

2.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.