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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.09

7:0.07

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

gard

-1.87

pei

-1.83

checked

-1.79

フォ

-1.79

itant

-1.78

hari

-1.72

hur

-1.72

charged

-1.71

stable

-1.70

bably

-1.70

POSITIVE LOGITS

 Cheong

1.74

 Stores

1.70

 conventions

1.67

 Movement

1.66

 Keys

1.57

 associ

1.57

 Groups

1.57

 movement

1.55

 Attacks

1.55

 inheritance

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.