INDEX

Explanations

phrases related to adherence or compliance with specified instructions or norms

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

phrases related to adherence or compliance with rules and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.01

1:0.02

2:0.10

3:0.17

4:0.02

5:0.03

6:0.04

7:0.09

8:0.06

9:0.22

10:0.08

11:0.11

Negative Logits

wow

-1.52

ERSON

-1.29

watching

-1.29

aukee

-1.23

erson

-1.19

whe

-1.17

DOWN

-1.15

IRO

-1.14

tumblr

-1.14

efe

-1.12

POSITIVE LOGITS

 criterion

1.32

 criteria

1.32

 strict

1.28

 rigid

1.22

 norms

1.19

 dictates

1.19

 stereotype

1.19

 fold

1.18

 script

1.18

 principles

1.17

Activations Density 0.005%

phrases related to adherence or compliance with specified instructions or norms

phrases related to adherence or compliance with rules and regulations

No Comments

No Known Activations