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

1:0.11

2:0.08

3:0.09

4:0.06

5:0.07

6:0.07

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

zan

-2.32

gar

-2.19

kar

-1.99

zie

-1.82

obar

-1.81

enth

-1.61

lly

-1.59

cest

-1.55

rim

-1.54

tor

-1.53

POSITIVE LOGITS

将

1.78

ulations

1.68

interstitial

1.64

RGB

1.62

Reloaded

1.60

ulation

1.55

ORPG

1.54

ECB

1.54

エ

1.49

 transfers

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.