INDEX

Explanations

words related to riding things or vehicles

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

references to riding various modes of transportation, particularly bicycles and horses

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

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

1:0.03

2:0.14

3:0.07

4:0.08

5:0.06

6:0.02

7:0.02

8:0.28

9:0.11

10:0.04

11:0.02

Negative Logits

zsche

-1.35

gemony

-1.23

inctions

-1.22

nces

-1.21

 distinguishing

-1.17

oteric

-1.17

rences

-1.16

hig

-1.13

gdala

-1.12

��

-1.10

POSITIVE LOGITS

 brakes

1.35

 roller

1.32

 fever

1.28

 wagon

1.28

 carts

1.27

ousel

1.26

roller

1.26

 broom

1.25

 heels

1.25

 stairs

1.22

Activations Density 0.009%

words related to riding things or vehicles

references to riding various modes of transportation, particularly bicycles and horses

No Comments

No Known Activations