INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.09

1:0.09

2:0.08

3:0.07

4:0.09

5:0.07

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

ahime

-3.20

STL

-2.96

DF

-2.87

SF

-2.77

 WRITE

-2.75

IL

-2.60

BDS

-2.57

RV

-2.50

iHUD

-2.44

DS

-2.43

POSITIVE LOGITS

soever

2.62

hower

2.37

\/\/

2.36

UG

2.36

 publicity

2.35

hirt

2.33

conscious

2.29

 coincided

2.24

iture

2.24

rh

2.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.