INDEX

Explanations

phrases related to cooking instructions and processes

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

0:0.03

1:0.31

2:0.02

3:0.20

4:0.04

5:0.06

6:0.04

7:0.06

8:0.03

9:0.02

10:0.08

11:0.04

Negative Logits

 nobody

-2.63

 ignored

-2.61

 nowhere

-2.59

 undeniable

-2.49

 undeniably

-2.48

 innumerable

-2.33

 nothing

-2.33

 existed

-2.33

 insufficient

-2.32

no

-2.29

POSITIVE LOGITS

ohm

2.66

 remainder

2.52

inches

2.29

urch

2.22

acter

2.13

parts

2.13

PLA

2.10

DAY

2.08

about

2.07

assembly

2.07

Activations Density 0.003%

phrases related to cooking instructions and processes

No Comments

No Known Activations