INDEX

Explanations

numerical data and references to specific quantities or ages

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

0:0.05

1:0.03

2:0.07

3:0.16

4:0.03

5:0.07

6:0.03

7:0.07

8:0.04

9:0.03

10:0.31

11:0.05

Negative Logits

 alive

-2.64

 vigorously

-2.57

 until

-2.52

 steadily

-2.47

 slowly

-2.47

 faithfully

-2.46

 altogether

-2.36

 diligently

-2.36

 continuing

-2.33

 before

-2.29

POSITIVE LOGITS

latable

2.52

interstitial

2.43

opter

2.23

CHAT

2.15

 Cosponsors

2.14

umbnail

2.02

boa

1.98

imgur

1.91

female

1.89

>)

1.88

Activations Density 0.002%

numerical data and references to specific quantities or ages

No Comments

No Known Activations