INDEX

Explanations

conjunctions and prepositions that indicate relationships between clauses or phrases

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.08

1:0.09

2:0.03

3:0.08

4:0.04

5:0.05

6:0.04

7:0.37

8:0.06

9:0.03

10:0.04

11:0.04

Negative Logits

 disg

-2.79

izoph

-2.67

anse

-2.64

++)

-2.55

below

-2.43

 lives

-2.34

 overboard

-2.28

姫

-2.27

 Kund

-2.22

ahime

-2.21

POSITIVE LOGITS

iOS

3.24

 iPhones

3.02

 Apple

2.94

iOS

2.92

 Garmin

2.89

 macOS

2.79

 iPhone

2.72

 Compass

2.66

 Motorola

2.64

addons

2.58

Activations Density 0.004%

conjunctions and prepositions that indicate relationships between clauses or phrases

No Comments

No Known Activations