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

0:0.10

1:0.06

2:0.08

3:0.08

4:0.07

5:0.07

6:0.07

7:0.07

8:0.10

9:0.08

10:0.08

11:0.07

Negative Logits

龍喚士

-2.22

 Nanto

-2.22

 istg

-2.09

DragonMagazine

-1.86

 charact

-1.85

 bask

-1.83

��

-1.82

 Kinnikuman

-1.79

romeda

-1.78

 rall

-1.73

POSITIVE LOGITS

 leaked

1.77

flat

1.69

 injection

1.62

changes

1.62

 suggestion

1.59

confirmed

1.59

 abortion

1.58

 misinformation

1.58

 violet

1.55

 erroneous

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.