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

0:0.08

1:0.07

2:0.09

3:0.07

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 Rubin

-1.70

 deductions

-1.70

aunder

-1.52

 thefts

-1.49

lees

-1.49

dab

-1.46

esters

-1.46

 McKenna

-1.43

 Cath

-1.41

Tac

-1.41

POSITIVE LOGITS

ModLoader

2.01

BIL

1.87

unity

1.85

フォ

1.85

ンジ

1.79

REDACTED

1.73

��

1.72

ク

1.72

antle

1.71

ende

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.