INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.08

10:0.06

11:0.09

Negative Logits

��

-2.81

antha

-2.62

ェ

-2.62

戦

-2.42

 Braun

-2.34

 Franz

-2.28

imester

-2.25

vae

-2.25

 Vand

-2.23

Bei

-2.23

POSITIVE LOGITS

 confir

2.74

eless

2.68

!'

2.67

dyn

2.67

)'

2.61

Dub

2.54

Tex

2.53

CTR

2.52

.'

2.48

Ware

2.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.