INDEX

Explanations

references to specific entities or characters within a narrative

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

0:0.08

1:0.04

2:0.05

3:0.03

4:0.05

5:0.04

6:0.28

7:0.02

8:0.04

9:0.25

10:0.02

11:0.04

Negative Logits

Dah

-3.58

 Haas

-3.48

Dh

-3.44

 Guild

-3.31

otaur

-3.31

lia

-3.31

halla

-3.27

Beh

-3.20

 Leth

-3.18

 Valhalla

-3.17

POSITIVE LOGITS

Pop

9.34

Pop

8.88

pop

7.89

POP

7.63

pop

7.29

 pops

6.04

 popup

5.26

 popped

5.16

 popcorn

5.16

 popping

5.05

Activations Density 0.006%

references to specific entities or characters within a narrative

No Comments

No Known Activations