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

1:0.08

2:0.08

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.08

11:0.07

Negative Logits

esson

-1.89

uminati

-1.64

chini

-1.63

 Galactic

-1.56

 promotions

-1.55

lasses

-1.55

annel

-1.48

 Sale

-1.45

 presidential

-1.45

eto

-1.45

POSITIVE LOGITS

�

1.86

1.83

方

1.80

iveness

1.54

 Liberties

1.52

payer

1.50

 Samar

1.50

 flourished

1.48

ually

1.47

ROR

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.