INDEX

Explanations

concepts related to distinctions and classifications within a discussion

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

0:0.36

1:0.02

2:0.19

3:0.06

4:0.03

5:0.04

6:0.03

7:0.03

8:0.03

9:0.04

10:0.08

11:0.02

Negative Logits

 Berks

-2.46

oaded

-2.29

edient

-2.28

 downloads

-2.28

esters

-2.27

 dumps

-2.27

 Hels

-2.27

 Roose

-2.24

 Sims

-2.19

Ts

-2.19

POSITIVE LOGITS

 blurred

4.18

 distinctions

3.48

 blurry

3.46

 distinction

3.21

 blur

3.09

wcs

2.92

 separ

2.82

 lens

2.81

 deline

2.77

 distinguishing

2.70

Activations Density 0.003%

concepts related to distinctions and classifications within a discussion

No Comments

No Known Activations