INDEX

Explanations

phrases indicating movement or change in 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_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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.01

2:0.14

3:0.07

4:0.07

5:0.03

6:0.05

7:0.30

8:0.04

9:0.05

10:0.08

11:0.08

Negative Logits

MRI

-1.72

tumblr

-1.65

atari

-1.41

 largeDownload

-1.38

Graph

-1.37

translation

-1.36

 depicts

-1.36

 summarizes

-1.30

probably

-1.29

 floated

-1.28

POSITIVE LOGITS

ドラ

1.56

phis

1.52

Spread

1.52

 confront

1.50

 FIGHT

1.50

 STOR

1.49

ebus

1.48

 deadly

1.46

 melee

1.45

igious

1.44

Activations Density 0.001%

phrases indicating movement or change in context

No Comments

No Known Activations