INDEX

Explanations

elements related to breaks and work-related conditions

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_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.7.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

2:0.14

3:0.04

4:0.02

5:0.04

6:0.04

7:0.05

8:0.05

9:0.05

10:0.37

11:0.04

Negative Logits

Gall

-2.60

 Gall

-2.36

uls

-2.34

anners

-2.29

uster

-2.27

kus

-2.21

uran

-2.21

 Moran

-2.20

avor

-2.19

uman

-2.17

POSITIVE LOGITS

 Breaking

3.82

Breaking

3.51

Break

3.46

 break

3.33

 Break

3.26

broken

3.19

 breaking

3.11

BRE

3.11

break

3.09

 broken

3.00

Activations Density 0.002%

elements related to breaks and work-related conditions

No Comments

No Known Activations