INDEX

Explanations

phrases and terms related to new product launches or announcements

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

1:0.01

2:0.09

3:0.06

4:0.14

5:0.02

6:0.04

7:0.34

8:0.02

9:0.04

10:0.08

11:0.08

Negative Logits

ilage

-1.59

�

-1.54

matter

-1.51

ascript

-1.50

ancial

-1.45

hya

-1.37

cale

-1.35

aintain

-1.34

venants

-1.34

lig

-1.33

POSITIVE LOGITS

new

1.62

 resurg

1.36

 Rising

1.35

 newcomers

1.33

 Toro

1.30

 anew

1.30

ドラゴン

1.30

 newcomer

1.29

rosso

1.27

 crossover

1.26

Activations Density 0.003%

phrases and terms related to new product launches or announcements

No Comments

No Known Activations