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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.09

2:0.09

3:0.08

4:0.09

5:0.06

6:0.08

7:0.07

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

-1.66

 engagement

-1.54

idays

-1.52

-1.50

 merchandise

-1.43

ricular

-1.41

aturday

-1.40

utral

-1.38

phrine

-1.37

 obligated

-1.37

POSITIVE LOGITS

RNA

1.59

aper

1.59

ARC

1.51

ORN

1.50

 Predator

1.43

 bark

1.41

Bam

1.39

Nar

1.34

Adapt

1.31

ATA

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.