INDEX

Explanations

statements involving personal relationships and conflicts

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.04

1:0.06

2:0.14

3:0.05

4:0.03

5:0.13

6:0.04

7:0.05

8:0.05

9:0.26

10:0.07

11:0.03

Negative Logits

bid

-1.61

abus

-1.46

 credential

-1.28

advertising

-1.18

ropolitan

-1.18

 indemn

-1.18

 procure

-1.15

abling

-1.15

 precautions

-1.13

iland

-1.11

POSITIVE LOGITS

 Luffy

1.59

POV

1.49

wik

1.35

 Lovecraft

1.27

 Wong

1.21

apesh

1.19

 Vander

1.16

Dialogue

1.16

Compan

1.15

 Samurai

1.14

Activations Density 0.070%

statements involving personal relationships and conflicts

No Comments

No Known Activations