INDEX

Explanations

references to social media interactions and engagement

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

0:0.14

1:0.03

2:0.06

3:0.04

4:0.03

5:0.06

6:0.12

7:0.04

8:0.05

9:0.33

10:0.03

11:0.02

Negative Logits

 Cato

-4.66

 Randolph

-4.40

Rand

-4.26

 pulp

-3.85

Tar

-3.55

xon

-3.36

 serpent

-3.36

Wak

-3.24

 condu

-3.21

龍

-3.19

POSITIVE LOGITS

 Instagram

8.31

 Instr

5.52

Inst

5.10

IG

4.43

 hasht

4.36

inst

4.11

 influ

4.02

agram

3.99

 nail

3.89

 selfies

3.88

Activations Density 0.003%

references to social media interactions and engagement

No Comments

No Known Activations