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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.05

2:0.07

3:0.08

4:0.09

5:0.08

6:0.09

7:0.09

8:0.07

9:0.09

10:0.08

11:0.08

Negative Logits

ocrates

-1.88

omez

-1.79

iliary

-1.72

omics

-1.70

ovember

-1.67

ゴン

-1.65

ÛÛ

-1.60

ucks

-1.58

enegger

-1.57

bernatorial

-1.52

POSITIVE LOGITS

figure

1.50

Cit

1.48

 practise

1.47

 landfall

1.44

mere

1.34

 Gree

1.34

heric

1.31

heet

1.31

 standard

1.30

stood

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.