INDEX

Explanations

terms related to finance, taxation, and regulations

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

0:0.16

1:0.09

2:0.06

3:0.05

4:0.04

5:0.14

6:0.05

7:0.02

8:0.17

9:0.07

10:0.04

11:0.04

Negative Logits

heartedly

-1.78

ishable

-1.73

ibly

-1.65

aciously

-1.64

requently

-1.49

urally

-1.41

 answ

-1.39

�

-1.37

ogle

-1.36

 Yemeni

-1.36

POSITIVE LOGITS

VA

1.62

 Reduction

1.59

 Helm

1.59

 extension

1.53

 Expansion

1.50

OVA

1.48

 Extension

1.43

 Bonus

1.42

BIP

1.41

etc

1.40

Activations Density 0.110%

terms related to finance, taxation, and regulations

No Comments

No Known Activations