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

1:0.06

2:0.08

3:0.09

4:0.05

5:0.09

6:0.09

7:0.09

8:0.07

9:0.08

10:0.10

11:0.06

Negative Logits

ici

-1.57

rade

-1.54

isch

-1.46

acia

-1.38

ric

-1.38

nr

-1.36

Sig

-1.35

eld

-1.35

iku

-1.34

ic

-1.33

POSITIVE LOGITS

 GOODMAN

1.37

 ObamaCare

1.35

 spectrum

1.32

 resistor

1.30

 Lyft

1.29

 phosphorus

1.27

 acronym

1.27

bestos

1.25

 railroad

1.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.