INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.07

2:0.08

3:0.07

4:0.07

5:0.09

6:0.08

7:0.07

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

yip

-3.36

 iodine

-3.02

ighthouse

-2.88

ouf

-2.83

Nun

-2.83

 Greenland

-2.82

 traitor

-2.69

 Nose

-2.67

skirts

-2.62

 Kenny

-2.60

POSITIVE LOGITS

WS

2.78

psc

2.57

SO

2.54

 Chrysler

2.52

Chance

2.51

 reperto

2.49

 offerings

2.45

wcs

2.44

zza

2.40

rollment

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.