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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.07

8:0.07

9:0.07

10:0.07

11:0.08

Negative Logits

 canvas

-2.44

 colored

-2.40

...

-2.38

 Hawaiian

-2.37

HI

-2.36

 reversible

-2.28

hod

-2.24

Fair

-2.24

 descriptive

-2.24

 Constantin

-2.23

POSITIVE LOGITS

gob

3.12

 gobl

2.85

GBT

2.82

 Breitbart

2.68

FactoryReloaded

2.67

FB

2.67

UCH

2.67

mber

2.64

龍契士

2.64

tf

2.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.