INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.07

1:0.08

2:0.08

3:0.09

4:0.07

5:0.08

6:0.06

7:0.09

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

 Scotia

-3.11

 Juno

-3.08

 Manitoba

-2.72

 Nasa

-2.58

 Mens

-2.55

 Alberta

-2.51

SNP

-2.44

MLA

-2.44

NDP

-2.44

 Mulcair

-2.43

POSITIVE LOGITS

\/\/

3.08

 prototyp

2.53

�

2.48

 essentials

2.46

 storytelling

2.39

 widgets

2.38

 wast

2.35

utral

2.34

kefeller

2.34

ufact

2.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.