INDEX

Explanations

names of TV shows and related terms

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

0:0.05

1:0.03

2:0.23

3:0.06

4:0.22

5:0.05

6:0.04

7:0.03

8:0.07

9:0.09

10:0.05

11:0.03

Negative Logits

gradient

-1.57

ć

-1.54

yip

-1.35

hua

-1.35

heric

-1.33

anchester

-1.33

 gradient

-1.31

pipe

-1.27

 flow

-1.24

���

-1.24

POSITIVE LOGITS

 Dent

1.44

rities

1.39

Cele

1.31

 Insider

1.29

Tea

1.28

Scot

1.26

 Rath

1.26

ttes

1.23

DonaldTrump

1.22

Bug

1.21

Activations Density 0.002%

names of TV shows and related terms

No Comments

No Known Activations