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

1:0.06

2:0.08

3:0.09

4:0.09

5:0.07

6:0.07

7:0.08

8:0.08

9:0.09

10:0.09

11:0.07

Negative Logits

SP

-1.73

 Latest

-1.63

 Bron

-1.54

 Explosive

-1.54

 Personal

-1.52

aneously

-1.52

WC

-1.51

 Lifetime

-1.50

 Neck

-1.49

signed

-1.48

POSITIVE LOGITS

ospels

1.77

bys

1.68

emis

1.67

ADRA

1.61

 mund

1.61

 caliphate

1.61

 Borders

1.60

pse

1.59

Aren

1.58

oslav

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.