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

0:0.07

1:0.07

2:0.09

3:0.07

4:0.08

5:0.07

6:0.07

7:0.09

8:0.09

9:0.08

10:0.08

11:0.09

Negative Logits

 Vanity

-1.82

 Blanc

-1.80

 aloud

-1.73

 teammate

-1.67

Ki

-1.66

Cay

-1.61

Nu

-1.60

 Sirius

-1.57

 Peterson

-1.56

 Tier

-1.55

POSITIVE LOGITS

rob

2.00

hyde

1.95

ウス

1.90

strap

1.78

WARE

1.76

erial

1.71

aunders

1.69

control

1.69

fuck

1.66

mone

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.