INDEX

Explanations

positive expressions related to personal experiences or emotions

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

0:0.08

1:0.02

2:0.09

3:0.02

4:0.26

5:0.03

6:0.03

7:0.07

8:0.14

9:0.03

10:0.12

11:0.06

Negative Logits

advertisement

-1.34

 recess

-1.23

oris

-1.20

 Accessed

-1.15

soft

-1.14

GOT

-1.08

reen

-1.06

ß

-1.04

 pent

-1.03

mosp

-1.01

POSITIVE LOGITS

yip

1.28

anmar

1.24

 grandparents

1.20

aeda

1.19

iasis

1.17

 someday

1.16

rier

1.14

itably

1.14

 Asylum

1.12

 toget

1.12

Activations Density 0.087%

positive expressions related to personal experiences or emotions

No Comments

No Known Activations