INDEX

Explanations

product recommendations and positive performance feedback

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

0:0.14

1:0.01

2:0.18

3:0.17

4:0.04

5:0.12

6:0.03

7:0.08

8:0.04

9:0.03

10:0.06

11:0.05

Negative Logits

 Genocide

-2.24

 Yiannopoulos

-2.21

events

-2.14

icipated

-2.10

Events

-2.10

 Agenda

-2.08

TEXT

-2.03

chapter

-2.02

Language

-1.99

Plot

-1.98

POSITIVE LOGITS

 warranty

3.43

 durability

3.38

 adjustable

3.17

erg

2.97

 warranties

2.86

 silicone

2.84

 Stainless

2.79

 stainless

2.79

 rubber

2.75

 nylon

2.75

Activations Density 0.670%

product recommendations and positive performance feedback

No Comments

No Known Activations