INDEX

Explanations

references to prominent musicians or bands

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

1:0.08

2:0.06

3:0.09

4:0.09

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.07

11:0.07

Negative Logits

reck

-2.47

eways

-2.46

 Photograph

-2.44

SPONSORED

-2.40

woman

-2.24

agn

-2.21

 Marilyn

-2.21

erial

-2.18

acid

-2.18

heid

-2.17

POSITIVE LOGITS

?????-

2.22

の�

2.20

 motivational

2.20

 therap

2.16

��

2.15

 Telecom

2.15

 happ

2.12

 organizational

2.09

 waivers

2.08

FPS

2.08

Activations Density 0.000%

references to prominent musicians or bands

No Comments

No Known Activations