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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.09

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

シャ

-1.73

aphael

-1.57

ゴン

-1.55

ギ

-1.54

テ

-1.50

ガ

-1.49

translation

-1.43

ズ

-1.43

ーン

-1.42

ド

-1.40

POSITIVE LOGITS

mins

1.64

 insulated

1.60

 advant

1.38

amins

1.34

 sandbox

1.33

kees

1.32

 mosqu

1.32

mercial

1.31

 surviv

1.31

 Surviv

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.