INDEX

Explanations

words related to geographical locations, especially with a focus on conflict or political events

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.07

1:0.03

2:0.28

3:0.05

4:0.18

5:0.06

6:0.03

7:0.03

8:0.06

9:0.10

10:0.05

11:0.02

Negative Logits

 Wonderland

-1.42

phe

-1.37

 Lawn

-1.36

spr

-1.30

 Turing

-1.26

 whiff

-1.20

 Gutierrez

-1.19

hol

-1.19

 Foss

-1.18

 Hermes

-1.16

POSITIVE LOGITS

inki

1.68

Adds

1.27

 wors

1.24

anium

1.19

ipal

1.17

astern

1.17

een

1.16

 annex

1.14

ens

1.13

sung

1.13

Activations Density 0.002%

words related to geographical locations, especially with a focus on conflict or political events

No Comments

No Known Activations