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

1:0.09

2:0.08

3:0.08

4:0.06

5:0.07

6:0.08

7:0.08

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

til

-2.73

PCR

-2.53

oxy

-2.52

 Romanian

-2.52

 formulas

-2.47

................................

-2.45

 Constantin

-2.45

RH

-2.43

 formula

-2.42

RL

-2.39

POSITIVE LOGITS

Dek

2.72

 Yong

2.65

Task

2.64

 Schwar

2.63

 deadliest

2.50

 Burst

2.45

ayne

2.43

selage

2.41

 volcan

2.40

 Kush

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.