INDEX

Explanations

references to interpersonal relationships or friendships

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

1:0.09

2:0.08

3:0.08

4:0.07

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

··

-2.60

ghazi

-2.58

 Clever

-2.58

Yaz

-2.56

 confir

-2.55

戦

-2.47

Mé

-2.46

 FANT

-2.41

mir

-2.40

�

-2.38

POSITIVE LOGITS

arry

3.35

aiman

3.00

 spinach

3.00

ellar

2.83

itional

2.69

netflix

2.68

tnc

2.57

opolis

2.57

 inline

2.54

plin

2.53

Activations Density 0.000%

references to interpersonal relationships or friendships

No Comments

No Known Activations