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

0:0.09

1:0.09

2:0.06

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.09

10:0.09

11:0.07

Negative Logits

buster

-2.80

DonaldTrump

-2.67

 bitcoin

-2.40

 Guantanamo

-2.40

 commissions

-2.34

 impeachment

-2.28

 tyrann

-2.28

 bank

-2.28

busters

-2.27

Gow

-2.25

POSITIVE LOGITS

onics

2.91

Pt

2.89

amel

2.83

shr

2.70

dylib

2.69

 Nebula

2.66

Surv

2.65

grad

2.65

 Rarity

2.60

NF

2.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.