INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.07

1:0.09

2:0.07

3:0.08

4:0.07

5:0.08

6:0.07

7:0.08

8:0.08

9:0.07

10:0.10

11:0.09

Negative Logits

��

-1.57

ADRA

-1.51

 Pigs

-1.36

�

-1.36

awaru

-1.35

aeper

-1.31

ら

-1.28

eah

-1.28

�

-1.26

etheless

-1.26

POSITIVE LOGITS

 orderly

1.56

"],

1.43

 organise

1.40

onductor

1.40

Ltd

1.39

/(

1.36

sf

1.33

.",

1.33

]]

1.31

 vacancy

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.