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

2:0.07

3:0.09

4:0.07

5:0.08

6:0.08

7:0.09

8:0.07

9:0.09

10:0.07

11:0.07

Negative Logits

archy

-1.80

ocent

-1.76

 SHALL

-1.72

opoly

-1.71

achus

-1.68

thy

-1.66

amily

-1.63

omon

-1.63

aci

-1.63

pmwiki

-1.62

POSITIVE LOGITS

Availability

1.82

VERTISEMENT

1.75

Rs

1.62

Relations

1.62

1.58

Icon

1.51

Quant

1.50

 quartz

1.49

 ceremonies

1.49

Iv

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.