INDEX

Explanations

proper nouns related to places or organizations

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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.09

5:0.08

6:0.06

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

 hypoc

-2.66

 Decre

-2.61

————

-2.61

istle

-2.53

 Schro

-2.51

 Rasmussen

-2.51

 negotiators

-2.50

Ner

-2.50

ieft

-2.43

 Dull

-2.39

POSITIVE LOGITS

Mp

3.00

sein

2.92

VICE

2.64

ydia

2.58

bys

2.56

 Manitoba

2.53

atre

2.52

 Romeo

2.52

 Oblivion

2.49

`.

2.49

Activations Density 0.000%

proper nouns related to places or organizations

No Known Activations