INDEX

Explanations

detailed mentions of monetary values

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

0:0.06

1:0.04

2:0.12

3:0.10

4:0.08

5:0.06

6:0.04

7:0.04

8:0.21

9:0.10

10:0.06

11:0.03

Negative Logits

xual

-1.25

 hemor

-1.18

ateg

-1.17

 Chain

-1.16

 EntityItem

-1.13

 nutshell

-1.13

HF

-1.12

��

-1.11

��

-1.09

 Strategy

-1.09

POSITIVE LOGITS

ordinate

1.13

 necessities

1.09

�

1.07

Pinterest

1.02

pes

1.00

orbit

1.00

Rub

1.00

DragonMagazine

0.99

 prostitute

0.96

pex

0.96

Activations Density 0.002%

detailed mentions of monetary values

No Comments

No Known Activations