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

1:0.07

2:0.09

3:0.08

4:0.10

5:0.07

6:0.08

7:0.09

8:0.08

9:0.05

10:0.07

11:0.07

Negative Logits

swer

-1.75

Bern

-1.54

 settled

-1.52

 necks

-1.47

 Bern

-1.47

enment

-1.45

EMBER

-1.44

uras

-1.39

@@

-1.38

EEE

-1.38

POSITIVE LOGITS

Downloadha

1.65

ams

1.60

ô

1.52

borgh

1.49

hoe

1.47

EH

1.46

pox

1.46

gey

1.43

 Artist

1.41

Fil

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.