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

0:0.09

1:0.08

2:0.08

3:0.09

4:0.09

5:0.07

6:0.07

7:0.08

8:0.09

9:0.08

10:0.07

11:0.07

Negative Logits

 Instrument

-1.43

atz

-1.32

ados

-1.32

 lect

-1.29

 instruments

-1.27

mel

-1.26

Tea

-1.26

gage

-1.25

�

-1.25

 transc

-1.25

POSITIVE LOGITS

enegger

1.92

 conjecture

1.59

ERC

1.50

Tokens

1.42

!--

1.35

KEN

1.35

igslist

1.34

EGIN

1.32

 succeed

1.31

starter

1.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.