INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

1:0.06

2:0.08

3:0.09

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 Sear

-3.21

 Units

-2.90

pmwiki

-2.89

Dos

-2.88

Ens

-2.88

 Motorola

-2.88

atts

-2.79

 Watts

-2.75

SPI

-2.65

 GPIO

-2.63

POSITIVE LOGITS

 timetable

2.77

 conc

2.55

 mould

2.53

 burying

2.42

 stump

2.42

 locality

2.41

 refund

2.41

 demolition

2.41

 hammer

2.35

 donate

2.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.