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

1:0.07

2:0.08

3:0.07

4:0.09

5:0.07

6:0.09

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

lyak

-1.59

◼

-1.54

atis

-1.52

ively

-1.40

lly

-1.39

brew

-1.36

zza

-1.35

ingly

-1.35

ulously

-1.34

oğ

-1.33

POSITIVE LOGITS

inventoryQuantity

1.57

Tokens

1.54

田

1.52

ixel

1.52

エル

1.37

姫

1.33

�

1.32

 Sands

1.31

igraph

1.30

ength

1.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.