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

0:0.09

1:0.06

2:0.08

3:0.07

4:0.08

5:0.07

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 Dual

-2.01

 Conversion

-1.86

 Cases

-1.84

Vs

-1.83

 Miscellaneous

-1.83

 Preferred

-1.74

 Ratio

-1.66

 Invention

-1.64

 Doctrine

-1.63

 Method

-1.63

POSITIVE LOGITS

oğ

1.99

heastern

1.96

agraph

1.85

idas

1.82

cffffcc

1.81

esi

1.76

gettable

1.72

seeing

1.70

watching

1.70

BuyableInstoreAndOnline

1.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.