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

0:0.09

1:0.10

2:0.06

3:0.07

4:0.08

5:0.07

6:0.09

7:0.07

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

Specific

-2.75

 Logged

-2.62

 Beam

-2.49

ient

-2.48

TPPStreamerBot

-2.47

Cert

-2.43

 pots

-2.43

Application

-2.40

ーク

-2.36

Qual

-2.35

POSITIVE LOGITS

 Stras

3.13

Duc

3.11

 Judaism

3.07

 Yose

2.94

 Auschwitz

2.86

Dj

2.85

 Rabbi

2.81

 Jordanian

2.79

Mog

2.75

 Africans

2.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.