INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

2:0.07

3:0.07

4:0.09

5:0.08

6:0.08

7:0.08

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

cellaneous

-1.58

levant

-1.52

lr

-1.41

pd

-1.40

ials

-1.40

filled

-1.38

asta

-1.33

attle

-1.32

inders

-1.29

unn

-1.29

POSITIVE LOGITS

 stripes

1.71

cale

1.68

 constitu

1.55

田

1.55

CEO

1.54

ドラゴン

1.43

GGGGGGGG

1.41

 horizont

1.40

 decentral

1.40

enance

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.