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

1:0.09

2:0.07

3:0.07

4:0.06

5:0.08

6:0.09

7:0.09

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

Lev

-2.84

NEC

-2.79

 Lite

-2.72

 Mutant

-2.54

 reader

-2.48

 Hebrew

-2.39

 ripple

-2.34

 Prediction

-2.33

Lev

-2.32

 viral

-2.29

POSITIVE LOGITS

|--

3.32

psc

3.10

uties

3.01

rentices

2.93

Frames

2.91

ayne

2.83

frames

2.79

fram

2.74

retty

2.73

unte

2.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.