INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.07

3:0.08

4:0.09

5:0.09

6:0.09

7:0.06

8:0.07

9:0.08

10:0.07

11:0.07

Negative Logits

 Cosponsors

-2.96

 Dwight

-2.88

reve

-2.50

 greenhouse

-2.44

 Refugee

-2.43

Resource

-2.40

 corridors

-2.36

zl

-2.35

 lobb

-2.34

 Wheel

-2.33

POSITIVE LOGITS

roy

2.86

Pol

2.73

uve

2.71

mortem

2.70

Duc

2.68

 coron

2.59

Au

2.53

Rai

2.50

 icing

2.45

orius

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.