INDEX

Explanations

questions and rhetorical statements

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

2:0.14

3:0.09

4:0.07

5:0.02

6:0.03

7:0.38

8:0.04

9:0.03

10:0.06

11:0.05

Negative Logits

mony

-1.71

ority

-1.64

icans

-1.59

urance

-1.56

enary

-1.54

Reviewer

-1.50

rowd

-1.49

uli

-1.46

zman

-1.44

iors

-1.43

POSITIVE LOGITS

 fate

1.61

 axes

1.56

 partName

1.51

 scissors

1.51

Klu

1.48

Option

1.42

 Fate

1.42

EG

1.39

 Hamb

1.38

?",

1.36

Activations Density 0.006%

questions and rhetorical statements

No Comments

No Known Activations