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

1:0.08

2:0.08

3:0.07

4:0.07

5:0.08

6:0.08

7:0.09

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

��

-4.06

udos

-2.95

Bloom

-2.75

 Credits

-2.72

 Damien

-2.71

WP

-2.63

displayText

-2.63

FB

-2.62

appa

-2.57

ateurs

-2.53

POSITIVE LOGITS

Wak

2.93

Hok

2.89

 Tart

2.86

ule

2.83

 Lith

2.80

 Xiang

2.71

 Slot

2.68

oshenko

2.64

 Tesla

2.63

 Siber

2.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.