INDEX

Explanations

proper nouns related to characters, movies, and pop culture references

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

1:0.04

2:0.26

3:0.07

4:0.15

5:0.07

6:0.02

7:0.03

8:0.07

9:0.10

10:0.06

11:0.03

Negative Logits

 spons

-1.44

bably

-1.36

akeru

-1.34

incial

-1.30

 showc

-1.24

atican

-1.19

vered

-1.19

iard

-1.17

olescent

-1.16

 substant

-1.15

POSITIVE LOGITS

 Swordsman

1.53

Runner

1.48

 Robotics

1.27

 Legends

1.21

 Adventures

1.20

 Bones

1.20

 Cortex

1.20

 Morph

1.19

 Reloaded

1.18

 Dwarf

1.15

Activations Density 0.007%

proper nouns related to characters, movies, and pop culture references

No Comments

No Known Activations