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

0:0.08

1:0.06

2:0.07

3:0.08

4:0.09

5:0.08

6:0.09

7:0.09

8:0.09

9:0.08

10:0.07

11:0.07

Negative Logits

IA

-1.80

idation

-1.51

 Opportun

-1.45

sylv

-1.42

 morale

-1.41

 fundraiser

-1.39

caster

-1.39

isher

-1.37

 Fishing

-1.37

PTS

-1.36

POSITIVE LOGITS

 leases

1.82

 handcuffs

1.63

uphem

1.60

 guards

1.52

unia

1.52

umbledore

1.52

pps

1.51

 taxis

1.49

 beds

1.49

awei

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.