INDEX

Explanations

words related to apologies and expressions of regret

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_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

0:0.03

1:0.02

2:0.11

3:0.14

4:0.07

5:0.06

6:0.05

7:0.18

8:0.06

9:0.08

10:0.08

11:0.06

Negative Logits

pleted

-1.48

Days

-1.44

 stalled

-1.34

hello

-1.34

Ready

-1.31

FILE

-1.30

DAY

-1.27

→

-1.24

 Gorsuch

-1.23

Tomorrow

-1.23

POSITIVE LOGITS

 surpr

1.62

Mub

1.57

 Param

1.52

raints

1.41

 Cloak

1.35

 incom

1.33

 embed

1.31

 Subtle

1.29

qua

1.28

qq

1.27

Activations Density 0.000%

words related to apologies and expressions of regret

No Comments

No Known Activations