INDEX

Explanations

references to music albums and performances

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

1:0.07

2:0.08

3:0.09

4:0.06

5:0.08

6:0.07

7:0.07

8:0.09

9:0.08

10:0.09

11:0.09

Negative Logits

 Ware

-2.32

 Tribunal

-2.29

 Cult

-2.28

liga

-2.21

 Industry

-2.17

 Selling

-2.15

 secondly

-2.13

 Saga

-2.12

 organis

-2.11

 Thou

-2.09

POSITIVE LOGITS

prus

2.35

colored

2.31

adelphia

2.26

Buff

2.24

Chuck

2.20

annie

2.18

scl

2.16

ュ

2.15

fixes

2.13

 carbohyd

2.12

Activations Density 0.000%

references to music albums and performances

No Comments

No Known Activations