INDEX

Explanations

mentions of music albums and their associated descriptions or reviews

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

0:0.06

1:0.07

2:0.20

3:0.06

4:0.03

5:0.03

6:0.22

7:0.10

8:0.02

9:0.05

10:0.10

11:0.03

Negative Logits

 resil

-2.89

 Pixie

-2.72

 Shine

-2.60

aza

-2.60

prem

-2.50

 Pengu

-2.47

kaya

-2.41

Raz

-2.40

FTC

-2.37

POSITIVE LOGITS

John

6.79

 John

6.59

 JOHN

5.82

JOHN

5.77

john

5.36

 john

4.62

 Johnston

4.24

 Johns

4.08

Johnny

3.17

Jon

3.15

Activations Density 0.063%

mentions of music albums and their associated descriptions or reviews

No Comments

No Known Activations