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

0:0.08

1:0.06

2:0.09

3:0.07

4:0.08

5:0.08

6:0.09

7:0.09

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

ire

-1.71

-1.41

-1.40

ports

-1.40

lys

-1.34

pass

-1.31

ward

-1.30

"],

-1.26

("

-1.24

 Senators

-1.22

POSITIVE LOGITS

 tiss

1.94

senal

1.84

utenberg

1.76

maxwell

1.72

utra

1.69

ensibly

1.68

 Beir

1.66

psey

1.65

�

1.60

uala

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.