INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.07

1:0.06

2:0.09

3:0.09

4:0.07

5:0.08

6:0.08

7:0.09

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

覚醒

-1.63

ADV

-1.50

 Prairie

-1.47

 Reincarnated

-1.46

 Precision

-1.46

senal

-1.44

Zac

-1.44

 Archdemon

-1.42

 National

-1.41

 Mercy

-1.39

POSITIVE LOGITS

ess

1.90

pload

1.75

──

1.63

pid

1.62

ulla

1.55

 adolesc

1.54

oids

1.52

rencies

1.52

accompanied

1.49

:]

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.