INDEX

Explanations

people and their roles in various fields, such as actors, authors, and singers

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

1:0.02

2:0.19

3:0.07

4:0.35

5:0.04

6:0.03

7:0.02

8:0.05

9:0.07

10:0.04

11:0.02

Negative Logits

 condol

-1.72

thora

-1.58

dayName

-1.48

oslav

-1.45

cdn

-1.44

oshenko

-1.42

��

-1.42

pload

-1.41

odd

-1.40

amiliar

-1.38

POSITIVE LOGITS

ATI

1.57

 STATS

1.38

 plank

1.35

 earners

1.30

 negotiator

1.26

 uptake

1.26

 Lead

1.25

 extraction

1.24

 mercury

1.24

 magnesium

1.23

Activations Density 0.009%

people and their roles in various fields, such as actors, authors, and singers

No Comments

No Known Activations