INDEX

Explanations

specific morphological patterns or formations in words, particularly focusing on prefixes and suffixes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

0:0.04

1:0.02

2:0.04

3:0.04

4:0.04

5:0.02

6:0.56

7:0.03

8:0.03

9:0.04

10:0.05

11:0.03

Negative Logits

 independents

-1.33

 accuser

-1.32

Ruk

-1.27

gat

-1.24

 Hank

-1.20

 edges

-1.18

 puppies

-1.15

 dogs

-1.14

anchester

-1.13

Topics

-1.12

POSITIVE LOGITS

ioxide

1.56

ophen

1.49

arte

1.41

odor

1.33

etric

1.27

ão

1.27

nell

1.27

insula

1.25

 Entered

1.25

lished

1.25

Activations Density 0.009%

specific morphological patterns or formations in words, particularly focusing on prefixes and suffixes

No Comments

No Known Activations