INDEX

Explanations

words indicating causality or consequence

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

0:0.03

1:0.02

2:0.04

3:0.03

4:0.12

5:0.18

6:0.02

7:0.05

8:0.01

9:0.37

10:0.02

11:0.06

Negative Logits

��

-2.29

 sqor

-2.23

assadors

-2.23

estones

-2.21

 Roof

-2.05

 These

-2.03

 Walls

-2.00

覚醒

-1.98

 Crest

-1.92

 gazed

-1.86

POSITIVE LOGITS

 arises

3.53

 affects

3.49

 occurs

3.37

 differs

3.35

 implies

3.30

 involves

3.22

 corresponds

3.21

 applies

3.19

 entails

3.19

 happens

3.16

Activations Density 0.437%

words indicating causality or consequence

No Comments

No Known Activations