INDEX

Explanations

phrases indicating duration or timeframes

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

0:0.03

1:0.02

2:0.06

3:0.05

4:0.05

5:0.04

6:0.37

7:0.13

8:0.03

9:0.06

10:0.06

11:0.05

Negative Logits

abee

-1.43

ptoms

-1.42

NAS

-1.42

apeake

-1.40

auga

-1.38

MAP

-1.37

rek

-1.36

aryl

-1.35

reys

-1.35

MSN

-1.32

POSITIVE LOGITS

��

1.54

 persuasion

1.46

 understatement

1.40

Mub

1.35

matter

1.31

 surpr

1.30

ohm

1.26

medi

1.22

 Waterloo

1.21

 Bris

1.20

Activations Density 0.004%

phrases indicating duration or timeframes

No Comments

No Known Activations