INDEX

Explanations

punctuation and sentence structure, particularly periods and conjunctions

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

0:0.12

1:0.02

2:0.10

3:0.11

4:0.03

5:0.06

6:0.02

7:0.02

8:0.29

9:0.07

10:0.06

11:0.06

Negative Logits

ilitary

-1.66

 eleph

-1.63

incial

-1.60

ghan

-1.57

mercial

-1.51

 premier

-1.46

plet

-1.46

 ascend

-1.45

issance

-1.43

ollah

-1.41

POSITIVE LOGITS

 Others

1.91

Others

1.85

etc

1.79

 Finally

1.75

Finally

1.67

 Taken

1.63

 Lastly

1.60

ighed

1.58

�

1.54

 Waiting

1.52

Activations Density 0.057%

punctuation and sentence structure, particularly periods and conjunctions

No Comments

No Known Activations