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

0:0.09

1:0.09

2:0.08

3:0.07

4:0.07

5:0.06

6:0.07

7:0.08

8:0.09

9:0.08

10:0.09

11:0.07

Negative Logits

rend

-1.49

rest

-1.39

ction

-1.37

gro

-1.36

actor

-1.36

roc

-1.35

roxy

-1.33

idable

-1.31

Corp

-1.31

Bro

-1.30

POSITIVE LOGITS

 arsen

1.50

 touting

1.46

advertisement

1.42

akuya

1.40

FTWARE

1.39

 Frie

1.38

 wedd

1.37

DPR

1.35

sonian

1.34

 imag

1.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.