INDEX

Explanations

expressions of hope and potential positive outcomes

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

1:0.02

2:0.06

3:0.33

4:0.03

5:0.08

6:0.02

7:0.05

8:0.03

9:0.02

10:0.23

11:0.02

Negative Logits

 raping

-1.95

HOME

-1.93

 guiActiveUn

-1.92

ˈ

-1.90

 preferring

-1.89

機

-1.88

 CONTROL

-1.86

 ostensibly

-1.86

ンジ

-1.85

OFF

-1.85

POSITIVE LOGITS

vind

2.36

 someday

2.33

 succeeds

2.30

 renaissance

2.28

 breakthrough

2.19

 revital

2.13

 reconciliation

2.11

 resonate

2.07

 inspires

2.04

 reconnect

2.02

Activations Density 0.168%

expressions of hope and potential positive outcomes

No Comments

No Known Activations