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

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.07

3:0.07

4:0.08

5:0.10

6:0.08

7:0.08

8:0.07

9:0.09

10:0.08

11:0.08

Negative Logits

liner

-1.50

 fade

-1.28

ecycle

-1.24

buster

-1.23

 risked

-1.22

Luk

-1.19

 whilst

-1.18

 Presence

-1.17

iability

-1.17

HMS

-1.15

POSITIVE LOGITS

 mathemat

1.76

cffff

1.71

idian

1.53

EEE

1.51

initialized

1.45

pees

1.45

soType

1.43

 UNCLASSIFIED

1.43

 coord

1.43

 agre

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.