INDEX

Explanations

information about a specific location or event

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

0:0.07

1:0.05

2:0.06

3:0.09

4:0.04

5:0.10

6:0.15

7:0.09

8:0.08

9:0.07

10:0.10

11:0.04

Negative Logits

 antagon

-1.39

 Carney

-1.32

 Canaver

-1.24

 negativity

-1.20

 heterogeneity

-1.19

CBD

-1.15

 homophobia

-1.12

 Angus

-1.12

黒

-1.11

 homophobic

-1.10

POSITIVE LOGITS

leans

1.38

artifacts

1.24

etheless

1.24

ilty

1.23

anwhile

1.19

pei

1.19

bye

1.15

Bug

1.11

 sprint

1.07

hement

1.07

Activations Density 0.001%

information about a specific location or event

No Comments

No Known Activations