INDEX

Explanations

mentions of 'The Guy' or variations indicative of a characterization of a male figure

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

0:0.04

1:0.09

2:0.06

3:0.05

4:0.02

5:0.04

6:0.07

7:0.06

8:0.03

9:0.05

10:0.35

11:0.09

Negative Logits

orn

-2.99

ORN

-2.71

onga

-2.49

saf

-2.32

orns

-2.29

Pand

-2.24

orah

-2.23

ORT

-2.22

onduct

-2.17

ort

-2.15

POSITIVE LOGITS

guy

4.33

 guys

3.91

 Guys

3.64

 dudes

3.57

 dude

3.30

guy

3.28

Guy

3.12

Guy

2.77

 folks

2.73

 buddies

2.71

Activations Density 0.003%

mentions of 'The Guy' or variations indicative of a characterization of a male figure

No Comments

No Known Activations