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

2:0.07

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.07

9:0.09

10:0.09

11:0.08

Negative Logits

Near

-3.08

 Tens

-2.88

BLE

-2.81

 Klingon

-2.76

cam

-2.74

Heb

-2.73

ocamp

-2.68

dfx

-2.63

ゼウス

-2.61

pu

-2.60

POSITIVE LOGITS

 resign

2.86

 superv

2.69

 advocacy

2.63

 billionaires

2.50

 millionaires

2.50

 resignation

2.50

itton

2.46

 dissent

2.41

DonaldTrump

2.38

 retirees

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.