INDEX

Explanations

references to the banking industry and financial misconduct

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.44

1:0.01

2:0.13

3:0.10

4:0.02

5:0.08

6:0.02

7:0.05

8:0.05

9:0.02

10:0.02

11:0.01

Negative Logits

 goggles

-2.36

 Gundam

-2.36

 manufact

-2.32

Rocket

-2.28

Sok

-2.24

fest

-2.23

 costume

-2.23

Hoo

-2.22

Reviewer

-2.16

 Sorceress

-2.14

POSITIVE LOGITS

 lender

5.24

 bank

5.03

 lending

4.97

Bank

4.96

 banking

4.95

 Bank

4.87

 Banking

4.79

 banks

4.73

 lenders

4.70

 loans

4.68

Activations Density 0.363%

references to the banking industry and financial misconduct

No Comments

No Known Activations