INDEX

Explanations

prepositions indicating relationships in a sentence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

2:0.08

3:0.06

4:0.12

5:0.03

6:0.05

7:0.33

8:0.03

9:0.05

10:0.07

11:0.08

Negative Logits

ordinary

-1.57

rex

-1.55

 istg

-1.54

common

-1.45

ateurs

-1.43

 Painter

-1.36

abee

-1.35

isons

-1.34

hee

-1.33

ather

-1.29

POSITIVE LOGITS

 accomplishments

1.62

 clin

1.58

 successes

1.55

 attendance

1.52

 predictions

1.51

 openings

1.49

 winning

1.47

 accomplishment

1.47

won

1.44

 accur

1.43

Activations Density 0.000%

prepositions indicating relationships in a sentence

No Comments

No Known Activations