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

1:0.07

2:0.08

3:0.07

4:0.07

5:0.09

6:0.09

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

ten

-2.89

assian

-2.88

pmwiki

-2.87

hedral

-2.83

acus

-2.81

Accessory

-2.77

 mould

-2.71

Interstitial

-2.66

ickets

-2.63

ynamic

-2.61

POSITIVE LOGITS

 Nikola

2.95

 Elon

2.70

 bailed

2.60

 iCloud

2.59

Jen

2.57

Tes

2.57

 Nvidia

2.50

 Nikki

2.50

 Amber

2.50

 JPMorgan

2.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.