INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.09

2:0.08

3:0.06

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

NCT

-1.74

utonium

-1.47

ivating

-1.42

ENTS

-1.40

ITED

-1.39

UC

-1.35

UF

-1.34

AGES

-1.34

mbuds

-1.31

eligible

-1.31

POSITIVE LOGITS

 shrine

1.50

tom

1.41

 amulet

1.37

 miscon

1.37

戦

1.35

bra

1.32

 gland

1.31

 sectarian

1.31

 Technique

1.30

 tile

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.