INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.08

2:0.10

3:0.07

4:0.08

5:0.07

6:0.08

7:0.07

8:0.08

9:0.07

10:0.10

11:0.08

Negative Logits

Ara

-1.75

ec

-1.65

Urs

-1.61

um

-1.61

 Legs

-1.53

 Miko

-1.52

 flank

-1.50

Aus

-1.49

 rooft

-1.48

Raf

-1.47

POSITIVE LOGITS

etheless

1.98

fixed

1.87

obar

1.75

ady

1.72

enabled

1.68

cham

1.67

hing

1.67

 Cheong

1.65

operated

1.64

creen

1.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.