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

0:0.08

1:0.05

2:0.06

3:0.07

4:0.08

5:0.07

6:0.09

7:0.10

8:0.09

9:0.09

10:0.08

11:0.07

Negative Logits

bis

-2.07

folio

-1.96

aucus

-1.80

undo

-1.79

 Detail

-1.78

odo

-1.74

aware

-1.70

folios

-1.69

cont

-1.68

erest

-1.66

POSITIVE LOGITS

 bets

1.79

 footsteps

1.72

 holster

1.72

 sticks

1.64

 racks

1.64

 sensit

1.63

 bells

1.62

 cigars

1.62

 tornado

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.