INDEX

Explanations

occurrences of the indefinite article "a."

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

IFrame

Link

Head Attr Weights

0:0.08

1:0.08

2:0.09

3:0.08

4:0.08

5:0.09

6:0.07

7:0.08

8:0.07

9:0.06

10:0.08

11:0.09

Negative Logits

��

-3.70

anchester

-3.05

sax

-3.04

webkit

-3.01

iments

-2.92

anguages

-2.79

cpp

-2.71

ゴン

-2.63

aq

-2.58

hovah

-2.56

POSITIVE LOGITS

 Greenpeace

2.58

cdn

2.56

GOT

2.46

 Nerd

2.43

ozy

2.38

DON

2.35

DER

2.27

DAC

2.24

 Launch

2.23

 environmentalists

2.23

Activations Density 0.000%

occurrences of the indefinite article "a."

No Known Activations