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

2:0.08

3:0.08

4:0.09

5:0.08

6:0.06

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

fug

-2.84

Weak

-2.77

 thief

-2.74

 roam

-2.68

 Warlock

-2.67

src

-2.63

Lock

-2.57

irrel

-2.54

Iterator

-2.53

 Cook

-2.53

POSITIVE LOGITS

[/

2.64

[/

2.63

ASA

2.47

Fet

2.46

cis

2.45

 controversial

2.45

NP

2.44

‎

2.43

 Wikimedia

2.40

 Suzuki

2.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.