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

1:0.05

2:0.09

3:0.09

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

 Rapids

-1.82

 Cater

-1.73

 Carbuncle

-1.68

 Chall

-1.67

 Corsair

-1.64

heard

-1.61

Wax

-1.54

 Shad

-1.54

 Mehran

-1.52

 Scare

-1.51

POSITIVE LOGITS

verning

2.30

 isEnabled

1.99

inventoryQuantity

1.93

 bipolar

1.76

 ecology

1.75

 サーティワン

1.75

cience

1.68

 epigen

1.67

 Leilan

1.64

 physiology

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.