INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.07

1:0.07

2:0.09

3:0.08

4:0.09

5:0.08

6:0.09

7:0.08

8:0.08

9:0.07

10:0.07

11:0.07

Negative Logits

enhagen

-1.67

.)

-1.60

Background

-1.55

emi

-1.50

 acknowled

-1.42

 aesthetics

-1.39

;;;;;;;;

-1.38

IDE

-1.37

ERG

-1.35

)--

-1.34

POSITIVE LOGITS

agram

1.50

 Maid

1.45

�

1.44

 theirs

1.43

square

1.43

 disinfect

1.43

 foothold

1.42

hare

1.38

(£

1.36

Yor

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.