INDEX

Explanations

elements related to character relationships and emotional dynamics

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.28

1:0.05

2:0.05

3:0.05

4:0.06

5:0.04

6:0.11

7:0.07

8:0.03

9:0.05

10:0.11

11:0.04

Negative Logits

Catal

-4.04

 Arlington

-3.57

 Rogers

-3.48

Pic

-3.45

 Saber

-3.38

Ric

-3.37

 Byzantine

-3.35

 carriers

-3.34

 Hamilton

-3.24

ACS

-3.19

POSITIVE LOGITS

 Judd

7.78

luaj

3.52

Suk

3.37

Hed

3.30

 Cambodia

3.17

 Cumm

3.16

 goblin

3.08

 Bangl

3.04

 Lank

3.03

 Myanmar

3.03

Activations Density 0.001%

elements related to character relationships and emotional dynamics

No Comments

No Known Activations