INDEX

Explanations

terms and phrases related to campaign finance and contributions

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

0:0.02

1:0.01

2:0.06

3:0.05

4:0.05

5:0.05

6:0.08

7:0.03

8:0.04

9:0.05

10:0.32

11:0.17

Negative Logits

romeda

-1.50

�

-1.43

etheless

-1.41

icho

-1.39

 archaeologists

-1.36

ESV

-1.36

vim

-1.35

ruary

-1.34

 Lunar

-1.33

 missionaries

-1.33

POSITIVE LOGITS

frequency

1.73

 Disclosure

1.63

phony

1.42

 quotas

1.40

 manipulation

1.34

rendered

1.31

 criminality

1.30

otine

1.29

 ratings

1.26

acters

1.24

Activations Density 0.001%

terms and phrases related to campaign finance and contributions

No Comments

No Known Activations