INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.05

2:0.09

3:0.07

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

 Loaded

-1.56

elight

-1.54

 Leone

-1.48

��極

-1.47

aternity

-1.42

Wee

-1.41

 Spirits

-1.39

��

-1.39

 Sunshine

-1.37

icent

-1.36

POSITIVE LOGITS

 subsequ

1.72

 hypothetical

1.64

 redress

1.63

 flaw

1.57

 takeoff

1.45

iott

1.39

 corrective

1.38

 markup

1.38

foreseen

1.37

 exploit

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.