INDEX

Explanations

phrases that imply possession or association within various contexts

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_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

0:0.02

1:0.01

2:0.12

3:0.07

4:0.09

5:0.03

6:0.20

7:0.22

8:0.02

9:0.04

10:0.06

11:0.07

Negative Logits

 Creed

-1.22

antine

-1.16

 portions

-1.15

 passages

-1.14

 batches

-1.11

sites

-1.10

vier

-1.09

 yourselves

-1.09

 traces

-1.09

 warrants

-1.08

POSITIVE LOGITS

rontal

1.45

thood

1.32

INO

1.25

UGH

1.22

munition

1.19

GBT

1.18

asma

1.17

BuyableInstoreAndOnline

1.17

TOR

1.16

mAh

1.16

Activations Density 0.020%

phrases that imply possession or association within various contexts

No Comments

No Known Activations