INDEX

Explanations

information related to social and environmental issues

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

the preposition "to" and its related expressions

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

0:0.05

1:0.02

2:0.14

3:0.04

4:0.29

5:0.03

6:0.03

7:0.02

8:0.20

9:0.08

10:0.05

11:0.01

Negative Logits

headed

-1.31

Cru

-1.25

 Hyde

-1.25

dra

-1.25

NUM

-1.24

atorium

-1.24

kered

-1.22

White

-1.21

TIT

-1.20

MH

-1.20

POSITIVE LOGITS

*/(

1.66

MpServer

1.48

 arrang

1.48

roleum

1.44

 propagate

1.39

enhagen

1.36

覚醒

1.35

minecraft

1.30

 cleanup

1.26

 amplify

1.26

Activations Density 0.013%

information related to social and environmental issues

the preposition "to" and its related expressions

No Comments

No Known Activations