INDEX

Explanations

nouns indicating roles or positions within a context

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

0:0.01

1:0.01

2:0.08

3:0.07

4:0.29

5:0.01

6:0.10

7:0.22

8:0.02

9:0.02

10:0.06

11:0.05

Negative Logits

ombs

-1.90

leave

-1.49

rouse

-1.48

rule

-1.46

romy

-1.46

 deadlines

-1.46

erity

-1.42

omever

-1.41

 budgets

-1.39

berus

-1.37

POSITIVE LOGITS

 Wonderland

1.39

aw

1.37

 Begins

1.32

vantage

1.31

 Guilty

1.31

 sounding

1.30

 profitable

1.29

entious

1.27

 ROCK

1.27

 Drunk

1.22

Activations Density 0.006%

nouns indicating roles or positions within a context

No Comments

No Known Activations