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

1:0.06

2:0.08

3:0.07

4:0.07

5:0.08

6:0.08

7:0.09

8:0.07

9:0.08

10:0.08

11:0.10

Negative Logits

changes

-1.87

Companies

-1.83

yards

-1.83

isal

-1.77

 allowance

-1.77

elong

-1.76

change

-1.75

caps

-1.75

borgh

-1.70

 allowances

-1.67

POSITIVE LOGITS

 Kali

1.81

 apes

1.80

emetery

1.80

ItemThumbnailImage

1.79

 Remix

1.73

 srfAttach

1.69

 Pigs

1.67

 lifeless

1.65

Champ

1.61

 Forensic

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.