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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.07

5:0.11

6:0.07

7:0.06

8:0.08

9:0.07

10:0.06

11:0.09

Negative Logits

 marks

-1.66

 vomiting

-1.61

 terminating

-1.52

 rooting

-1.51

 spotting

-1.45

 pronounced

-1.45

MpServer

-1.43

 supers

-1.41

 rite

-1.40

 breathing

-1.40

POSITIVE LOGITS

ÃÂ

1.69

omics

1.63

istine

1.63

ieu

1.59

 Fisheries

1.59

udence

1.55

olesterol

1.54

 Sustainable

1.52

$,

1.52

idelines

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.