INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.07

2:0.07

3:0.08

4:0.09

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

ogun

-1.89

��

-1.65

ijk

-1.55

inic

-1.37

 Scotia

-1.36

gger

-1.35

 defer

-1.33

yg

-1.31

ulic

-1.30

 Sparkle

-1.30

POSITIVE LOGITS

BILITIES

1.71

Whereas

1.51

styles

1.49

stood

1.49

than

1.44

ANC

1.44

ortunately

1.42

 charact

1.40

asma

1.40

ARCH

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.