INDEX

Explanations

conjunctions and phrases indicating action or decision-making

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

New Auto-Interp

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

0:0.01

1:0.01

2:0.05

3:0.07

4:0.20

5:0.02

6:0.17

7:0.27

8:0.03

9:0.02

10:0.04

11:0.04

Negative Logits

soever

-1.70

olphin

-1.59

 dignity

-1.55

interstitial

-1.55

inion

-1.55

-1.49

grave

-1.45

Thumbnail

-1.44

 Thumbnails

-1.43

ggles

-1.41

POSITIVE LOGITS

soDeliveryDate

1.79

 Wass

1.49

acci

1.45

 Chip

1.43

anza

1.36

um

1.34

 Paddock

1.33

pmwiki

1.32

 Ruff

1.30

 Speedway

1.29

Activations Density 0.005%

conjunctions and phrases indicating action or decision-making

No Comments

No Known Activations