INDEX

Explanations

connective words that indicate relationships between ideas

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

0:0.09

1:0.07

2:0.08

3:0.09

4:0.08

5:0.08

6:0.07

7:0.08

8:0.10

9:0.08

10:0.06

11:0.07

Negative Logits

SPONSORED

-3.20

 Muss

-2.85

Mou

-2.56

VG

-2.37

 Music

-2.35

Myr

-2.34

 coincided

-2.34

 Brexit

-2.34

 UKIP

-2.33

 Yanukovych

-2.33

POSITIVE LOGITS

zai

3.08

unal

2.88

ンジ

2.72

aign

2.68

uni

2.65

venture

2.58

anus

2.56

 Dunham

2.56

inn

2.54

sten

2.53

Activations Density 0.000%

connective words that indicate relationships between ideas

No Comments

No Known Activations