INDEX

Explanations

references to locations and actions related to travel or migration

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.02

1:0.04

2:0.10

3:0.02

4:0.03

5:0.08

6:0.12

7:0.19

8:0.06

9:0.07

10:0.12

11:0.08

Negative Logits

 genius

-1.19

aneous

-1.15

ulative

-1.12

ctive

-1.12

 stature

-1.09

itious

-1.07

Gy

-1.05

 differential

-1.04

 Trends

-1.02

 intelligent

-1.01

POSITIVE LOGITS

idges

1.58

fecture

1.36

rongh

1.30

iland

1.27

 enclave

1.25

 whence

1.24

obos

1.21

viol

1.20

 annex

1.16

addons

1.16

Activations Density 0.171%

references to locations and actions related to travel or migration

No Comments

No Known Activations