INDEX

Explanations

phrases related to alerts and warnings

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

2:0.08

3:0.06

4:0.11

5:0.02

6:0.04

7:0.30

8:0.04

9:0.03

10:0.12

11:0.09

Negative Logits

advertising

-1.55

bowl

-1.54

cart

-1.46

ublic

-1.39

Pic

-1.38

田

-1.36

taining

-1.36

adr

-1.34

inth

-1.33

utan

-1.32

POSITIVE LOGITS

 alert

1.77

 vigilance

1.56

 arrival

1.53

 anticipation

1.48

 lest

1.47

urst

1.39

 midday

1.39

 Skydragon

1.39

 surges

1.36

 conting

1.35

Activations Density 0.001%

phrases related to alerts and warnings

No Comments

No Known Activations