INDEX

Explanations

phrases indicating a large quantity or variety of something

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

0:0.03

1:0.03

2:0.15

3:0.11

4:0.13

5:0.03

6:0.11

7:0.05

8:0.05

9:0.03

10:0.09

11:0.13

Negative Logits

 Received

-1.54

 Ashe

-1.45

Bec

-1.37

ihad

-1.35

arenthood

-1.35

issance

-1.35

 Into

-1.30

ufact

-1.28

Gas

-1.22

 Became

-1.22

POSITIVE LOGITS

raints

1.86

 similarities

1.75

 indications

1.75

 caveats

1.61

 psychiatrists

1.55

namese

1.53

 anecdotal

1.49

 disclaim

1.47

arij

1.46

 overlap

1.45

Activations Density 0.048%

phrases indicating a large quantity or variety of something

No Comments

No Known Activations