INDEX

Explanations

references to specific geographical locations

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

0:0.06

1:0.02

2:0.12

3:0.07

4:0.06

5:0.02

6:0.13

7:0.07

8:0.11

9:0.09

10:0.13

11:0.07

Negative Logits

apego

-1.36

irlf

-1.30

rency

-1.18

roach

-1.17

vantage

-1.12

comfort

-1.11

aper

-1.10

uler

-1.09

hower

-1.08

oice

-1.08

POSITIVE LOGITS

 locality

1.47

 guise

1.24

 vicinity

1.22

soDeliveryDate

1.21

 precincts

1.20

 circles

1.19

 Fields

1.16

 classrooms

1.14

 amph

1.14

 Halls

1.13

Activations Density 0.070%

references to specific geographical locations

No Comments

No Known Activations