INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

0:0.09

1:0.09

2:0.07

3:0.05

4:0.06

5:0.08

6:0.07

7:0.07

8:0.07

9:0.10

10:0.08

11:0.12

Negative Logits

blance

-1.57

ANC

-1.44

 heritage

-1.41

 diffusion

-1.37

iety

-1.34

ADRA

-1.33

 resonance

-1.33

 movements

-1.32

QUEST

-1.31

ⓘ

-1.30

POSITIVE LOGITS

agues

1.55

vs

1.52

kees

1.48

 Kers

1.44

 Purg

1.41

 Shotgun

1.39

ovie

1.38

 understatement

1.36

yp

1.31

 Hacker

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.