INDEX

Explanations

present participle verbs ending in 'ing' related to technical or operational activities

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

gerunds, particularly in context with actions and processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.53

1:0.02

2:0.03

3:0.02

4:0.06

5:0.03

6:0.05

7:0.05

8:0.03

9:0.03

10:0.06

11:0.03

Negative Logits

 Saur

-1.49

 ACTIONS

-1.44

 subscribing

-1.41

 Leia

-1.39

theless

-1.39

BuyableInstoreAndOnline

-1.37

Vi

-1.36

STAR

-1.36

paralle

-1.35

 arresting

-1.35

POSITIVE LOGITS

ings

3.03

ing

2.65

INGS

2.59

ING

2.13

ership

2.08

eport

2.04

zon

2.04

ning

2.00

utters

1.89

ers

1.87

Activations Density 0.497%

present participle verbs ending in 'ing' related to technical or operational activities

gerunds, particularly in context with actions and processes

No Comments

No Known Activations