INDEX

Explanations

phrases indicating relationships or connections between entities

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

0:0.02

1:0.02

2:0.05

3:0.05

4:0.13

5:0.03

6:0.03

7:0.41

8:0.02

9:0.03

10:0.08

11:0.07

Negative Logits

igm

-1.50

lynn

-1.44

 ships

-1.44

 planes

-1.37

quartered

-1.37

bones

-1.34

isode

-1.32

 transports

-1.31

 dissolved

-1.30

dule

-1.29

POSITIVE LOGITS

 underdog

1.84

MpServer

1.50

 deserved

1.43

 Against

1.41

Merit

1.39

du

1.37

 Winners

1.37

axe

1.36

 awards

1.36

 victory

1.34

Activations Density 0.003%

phrases indicating relationships or connections between entities

No Comments

No Known Activations