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

1:0.08

2:0.08

3:0.09

4:0.09

5:0.07

6:0.07

7:0.07

8:0.07

9:0.09

10:0.08

11:0.07

Negative Logits

adh

-2.85

 Haiti

-2.80

 improv

-2.77

Fas

-2.64

arella

-2.59

 Donation

-2.58

atem

-2.51

avez

-2.50

 Haven

-2.49

 traff

-2.49

POSITIVE LOGITS

[/

2.42

 Pluto

2.38

2.35

Pokémon

2.34

 Leafs

2.33

FIR

2.30

ocket

2.29

rium

2.29

 Polaris

2.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.