INDEX

Explanations

information related to prizes, awards, and competition rules

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

0:0.08

1:0.04

2:0.06

3:0.05

4:0.07

5:0.03

6:0.19

7:0.18

8:0.03

9:0.04

10:0.05

11:0.11

Negative Logits

 disapprove

-2.67

 Jindal

-2.50

etsy

-2.46

aments

-2.41

 filibuster

-2.38

 Passing

-2.35

 pass

-2.27

ierre

-2.24

 Romeo

-2.24

ullivan

-2.19

POSITIVE LOGITS

 prize

4.61

 prizes

4.59

 Prize

4.07

Pri

3.90

Pri

3.47

 Starcraft

3.38

MLG

3.08

 StarCraft

2.88

 Winners

2.87

 Winner

2.86

Activations Density 0.014%

information related to prizes, awards, and competition rules

No Comments

No Known Activations