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

3:0.08

4:0.07

5:0.07

6:0.08

7:0.08

8:0.09

9:0.07

10:0.09

11:0.08

Negative Logits

BMC

-1.29

uff

-1.21

iac

-1.21

gp

-1.21

iard

-1.18

ories

-1.18

 registers

-1.16

nt

-1.15

 itself

-1.15

netflix

-1.12

POSITIVE LOGITS

��

1.72

ratulations

1.54

 distingu

1.50

assad

1.43

ッド

1.41

��

1.41

��

1.40

 fundament

1.39

��

1.39

 appointment

1.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.