INDEX

Explanations

occurrences of winning in a competitive context

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

1:0.03

2:0.09

3:0.10

4:0.05

5:0.10

6:0.05

7:0.06

8:0.27

9:0.04

10:0.05

11:0.04

Negative Logits

 Lara

-3.00

 Ranch

-2.99

 Sunny

-2.91

 Whedon

-2.79

backer

-2.78

 Slim

-2.75

 Manziel

-2.72

 Buffy

-2.72

 Vista

-2.69

ounty

-2.68

POSITIVE LOGITS

 pawn

3.31

 rook

3.26

 Polish

3.23

 Ukrainians

3.15

 Ukrainian

3.07

 Georgian

3.04

 Poland

2.83

 Alexand

2.79

 Kiev

2.76

 Lithuan

2.75

Activations Density 0.002%

occurrences of winning in a competitive context

No Comments

No Known Activations