INDEX

Explanations

phrases indicating presence and ownership

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

1:0.02

2:0.11

3:0.07

4:0.22

5:0.03

6:0.17

7:0.05

8:0.03

9:0.04

10:0.09

11:0.09

Negative Logits

scill

-1.67

 compass

-1.46

isphere

-1.45

 microscope

-1.44

endas

-1.43

 forecasts

-1.43

 Franchise

-1.40

 prophets

-1.39

 prophe

-1.38

reci

-1.35

POSITIVE LOGITS

 manageable

1.51

 unaccompanied

1.49

 sparing

1.48

 Participant

1.38

GGGGGGGG

1.38

TAG

1.32

 Detention

1.27

 culmin

1.26

"}

1.24

 Schwar

1.24

Activations Density 0.003%

phrases indicating presence and ownership

No Comments

No Known Activations