INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.04

1:0.11

2:0.19

3:0.05

4:0.04

5:0.06

6:0.08

7:0.07

8:0.06

9:0.05

10:0.12

11:0.08

Negative Logits

 Literature

-2.56

 Forgotten

-2.51

Mem

-2.44

 Cemetery

-2.43

 Fore

-2.41

 Future

-2.40

 Univers

-2.37

 Leilan

-2.35

 Ecology

-2.34

 Hungry

-2.33

POSITIVE LOGITS

add

2.70

 strap

2.46

 unlocks

2.39

Add

2.26

aryl

2.24

enh

2.23

add

2.21

 overload

2.12

 boost

2.08

 unlock

2.08

Activations Density 0.000%

No Known Activations

This feature has no known activations.