INDEX

Explanations

negative sentiments and criticisms related to societal norms and constraints

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.06

2:0.03

3:0.03

4:0.03

5:0.01

6:0.06

7:0.49

8:0.03

9:0.03

10:0.10

11:0.04

Negative Logits

 Dixon

-3.48

Dar

-3.35

Dai

-3.34

Dh

-3.14

 Dani

-3.14

 Dong

-3.06

 Dawn

-3.01

DI

-2.96

dar

-2.88

Duc

-2.88

POSITIVE LOGITS

 Prism

2.39

ベ

2.39

["

2.31

2.26

"],"

2.23

Roaming

2.22

 Spears

2.21

<@

2.17

"]=>

2.17

2.15

Activations Density 0.209%

negative sentiments and criticisms related to societal norms and constraints

No Comments

No Known Activations