INDEX

Explanations

contrasting opinions or critiques in writing samples

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

0:0.06

1:0.02

2:0.12

3:0.11

4:0.09

5:0.09

6:0.05

7:0.04

8:0.14

9:0.11

10:0.08

11:0.04

Negative Logits

beam

-1.18

 vessel

-1.14

idge

-1.11

 Rack

-1.07

 specimen

-1.04

DOM

-1.03

 discrep

-1.03

 Primary

-0.99

eret

-0.99

Shape

-0.97

POSITIVE LOGITS

hett

1.25

aturday

1.23

pport

1.21

agara

1.19

ombies

1.19

ь

1.15

plete

1.12

achev

1.11

urg

1.09

conom

1.09

Activations Density 0.103%

contrasting opinions or critiques in writing samples

No Comments

No Known Activations