INDEX

Explanations

phrases related to economic or financial impacts

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.02

2:0.03

3:0.03

4:0.03

5:0.18

6:0.02

7:0.04

8:0.01

9:0.51

10:0.01

11:0.03

Negative Logits

hur

-2.06

resa

-2.02

�

-1.99

uggest

-1.97

hib

-1.93

 discourage

-1.86

BuyableInstoreAndOnline

-1.83

 sidx

-1.80

 reminder

-1.80

 illustrate

-1.78

POSITIVE LOGITS

via

3.76

by

3.67

by

3.46

 using

3.43

ardless

3.34

via

3.23

Via

3.09

 through

3.08

matically

3.07

By

2.90

Activations Density 1.077%

phrases related to economic or financial impacts

No Comments

No Known Activations