INDEX

Explanations

significant temporal indicators and dates within the text

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

1:0.01

2:0.12

3:0.06

4:0.07

5:0.03

6:0.10

7:0.32

8:0.03

9:0.02

10:0.07

11:0.10

Negative Logits

 distraction

-1.37

soType

-1.36

姫

-1.33

 behavi

-1.32

emis

-1.30

REF

-1.29

IELD

-1.28

 vigilant

-1.25

 neglected

-1.25

WF

-1.24

POSITIVE LOGITS

 Lancaster

1.45

phabet

1.42

runs

1.42

qus

1.41

sburgh

1.38

 sequ

1.36

 playthrough

1.35

assembly

1.34

cible

1.32

sembly

1.32

Activations Density 0.007%

significant temporal indicators and dates within the text

No Comments

No Known Activations