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

0:0.08

1:0.08

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.07

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

 Makoto

-2.71

 sacrific

-2.61

EGIN

-2.59

 Activision

-2.59

Admin

-2.55

 ACPI

-2.42

 sacr

-2.37

cmd

-2.36

FAA

-2.34

 certs

-2.34

POSITIVE LOGITS

igmatic

2.77

 gelatin

2.58

ils

2.53

onite

2.50

hill

2.47

utenberg

2.46

rils

2.40

 glossy

2.37

Goo

2.37

Kil

2.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.