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

0:0.07

1:0.07

2:0.08

3:0.07

4:0.08

5:0.06

6:0.09

7:0.08

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

 reality

-1.71

QC

-1.68

 caution

-1.57

 Ground

-1.50

raviolet

-1.50

��

-1.47

rette

-1.45

akable

-1.44

�

-1.43

oubt

-1.41

POSITIVE LOGITS

 Perse

1.85

esses

1.81

 fleets

1.80

 Mehran

1.69

Joined

1.69

opsis

1.63

 Leilan

1.63

Cod

1.59

�

1.59

bernatorial

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.