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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.07

8:0.07

9:0.07

10:0.08

11:0.10

Negative Logits

enei

-1.93

andowski

-1.93

ividual

-1.83

ilaterally

-1.73

 specialization

-1.70

 proport

-1.69

heastern

-1.69

 skelet

-1.60

alions

-1.56

 physicists

-1.56

POSITIVE LOGITS

シャ

1.78

 liquor

1.69

 champagne

1.68

FY

1.65

 Prohibition

1.60

BuyableInstoreAndOnline

1.59

 Savings

1.57

 Spotify

1.51

beer

1.50

rab

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.