INDEX

Explanations

information related to the effects of sodium and hydration on bodily functions

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

Head Attr Weights

0:0.16

1:0.10

2:0.11

3:0.05

4:0.05

5:0.01

6:0.06

7:0.12

8:0.02

9:0.04

10:0.16

11:0.06

Negative Logits

 Benn

-3.68

Beast

-3.36

 Beast

-3.11

 Witcher

-3.10

EVE

-2.95

 Bike

-2.74

wen

-2.74

 Vikings

-2.72

 Brend

-2.65

Beck

-2.65

POSITIVE LOGITS

 sodium

7.22

 Sodium

6.54

 potassium

5.54

assium

5.43

 chloride

4.96

odium

4.64

Na

4.52

 magnesium

4.32

 salt

4.23

Na

4.10

Activations Density 0.005%

information related to the effects of sodium and hydration on bodily functions

No Known Activations