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

5:0.08

6:0.07

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 Alleg

-2.44

cks

-2.42

security

-2.40

ulner

-2.37

prep

-2.37

FG

-2.35

>(

-2.33

GPA

-2.30

vp

-2.29

Growing

-2.23

POSITIVE LOGITS

 Canaver

2.83

 interven

2.77

 latex

2.75

flies

2.66

 typew

2.64

 filament

2.55

 promul

2.51

elaide

2.45

icester

2.44

ython

2.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.