INDEX

Explanations

different prepositions and conjunctions that indicate relationships or connections 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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.16

1:0.09

2:0.07

3:0.08

4:0.06

5:0.04

6:0.09

7:0.08

8:0.06

9:0.08

10:0.09

11:0.06

Negative Logits

 Diaz

-3.87

 Stanton

-3.35

 Django

-3.22

ullivan

-3.15

arag

-3.05

 Nieto

-2.94

SAP

-2.88

JFK

-2.86

SJ

-2.76

 Ferdinand

-2.73

POSITIVE LOGITS

Heb

6.28

Palest

3.61

udeb

3.35

 Rabb

3.27

 Jerusalem

3.27

 Palestinian

3.25

lehem

3.24

 Bethlehem

3.20

 Jericho

3.13

 Palestinians

3.07

Activations Density 0.001%

different prepositions and conjunctions that indicate relationships or connections between ideas

No Comments

No Known Activations