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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.07

3:0.09

4:0.09

5:0.08

6:0.10

7:0.09

8:0.07

9:0.07

10:0.07

11:0.08

Negative Logits

う

-2.33

lig

-2.31

ettes

-2.19

 pleas

-2.15

 unconditional

-2.12

 feminine

-2.08

jo

-2.07

 padd

-2.06

tro

-2.03

 closure

-2.02

POSITIVE LOGITS

adan

2.72

ultan

2.70

renheit

2.61

alore

2.58

IDA

2.54

kef

2.50

arcity

2.49

ushima

2.48

coni

2.44

paio

2.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.