INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.07

2:0.09

3:0.06

4:0.07

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.10

11:0.09

Negative Logits

raft

-1.64

Lock

-1.51

Chat

-1.46

rab

-1.43

arre

-1.41

vale

-1.36

ses

-1.31

rus

-1.28

 Lock

-1.28

atcher

-1.27

POSITIVE LOGITS

lihood

1.83

anwhile

1.75

 withd

1.75

 Tanz

1.74

enegger

1.68

 largeDownload

1.65

 Ukrain

1.64

�

1.63

��極

1.59

▬

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.