INDEX

Explanations

references to immigration-related topics and issues

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

1:0.05

2:0.24

3:0.06

4:0.05

5:0.07

6:0.03

7:0.04

8:0.04

9:0.22

10:0.08

11:0.03

Negative Logits

yss

-1.61

dfx

-1.56

SOURCE

-1.33

mallow

-1.30

ussian

-1.28

undred

-1.28

ODY

-1.26

akura

-1.26

pole

-1.25

RAY

-1.25

POSITIVE LOGITS

 felon

1.49

 caucuses

1.40

 cert

1.32

 Accountability

1.28

BLM

1.24

AMA

1.21

 amnesty

1.19

 marathon

1.19

 Compliance

1.19

 Cert

1.18

Activations Density 0.020%

references to immigration-related topics and issues

No Comments

No Known Activations