INDEX

Explanations

temporal phrases and sequences

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

0:0.05

1:0.07

2:0.10

3:0.19

4:0.05

5:0.05

6:0.04

7:0.16

8:0.06

9:0.08

10:0.06

11:0.04

Negative Logits

``

-2.98

...)

-2.86

Nap

-2.75

 Perth

-2.69

...]

-2.61

�

-2.46

''

-2.44

---

-2.42

 Picard

-2.36

Nap

-2.36

POSITIVE LOGITS

 Dunham

2.57

until

2.44

HB

2.37

cv

2.33

Address

2.29

oof

2.27

MK

2.27

ocy

2.26

mony

2.23

DOE

2.19

Activations Density 0.008%

temporal phrases and sequences

No Comments

No Known Activations