INDEX

Explanations

references to ingredients in recipes

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.01

2:0.09

3:0.06

4:0.08

5:0.05

6:0.04

7:0.08

8:0.04

9:0.05

10:0.30

11:0.13

Negative Logits

soDeliveryDate

-1.53

 anniversary

-1.46

conom

-1.37

 Teaching

-1.35

iphate

-1.35

thood

-1.34

ateurs

-1.33

 Teachers

-1.31

 Lessons

-1.31

 lessons

-1.31

POSITIVE LOGITS

 ingred

1.44

enta

1.40

appropriately

1.31

 proport

1.26

plex

1.26

zl

1.26

otion

1.25

chlor

1.21

changed

1.19

acted

1.18

Activations Density 0.014%

references to ingredients in recipes

No Comments

No Known Activations