INDEX

Explanations

No Explanations Found

New Auto-Interp

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

0:0.12

1:0.07

2:0.09

3:0.08

4:0.09

5:0.07

6:0.06

7:0.07

8:0.08

9:0.06

10:0.07

11:0.08

Negative Logits

 heterogeneity

-1.53

 Weeks

-1.53

INT

-1.53

 iceberg

-1.52

eki

-1.50

 horizont

-1.49

 traps

-1.49

 scaff

-1.49

ruciating

-1.46

 uncertainties

-1.45

POSITIVE LOGITS

��

1.89

��

1.81

サ

1.76

 sightings

1.72

oland

1.64

idae

1.63

 Masquerade

1.63

obyl

1.58

 CLSID

1.58

omics

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.