INDEX

Explanations

prepositions and phrases indicating direction or location

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

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.01

2:0.04

3:0.04

4:0.10

5:0.02

6:0.09

7:0.34

8:0.03

9:0.03

10:0.10

11:0.12

Negative Logits

 Factor

-1.41

 GOODMAN

-1.38

 Tale

-1.34

 weeds

-1.32

 Indigo

-1.31

 Towns

-1.31

 Conv

-1.30

 Transcript

-1.29

 Fever

-1.28

 Deaths

-1.27

POSITIVE LOGITS

eca

1.50

interstitial

1.39

iosyn

1.37

leasing

1.37

ranch

1.35

 maximizing

1.35

esa

1.35

 aiming

1.33

 squarely

1.33

ット

1.30

Activations Density 0.012%

prepositions and phrases indicating direction or location

No Comments

No Known Activations