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

2:0.10

3:0.09

4:0.10

5:0.07

6:0.07

7:0.07

8:0.09

9:0.08

10:0.08

11:0.07

Negative Logits

stuff

-1.73

etimes

-1.70

 Rolls

-1.65

atile

-1.46

ixtape

-1.44

 Must

-1.42

CVE

-1.38

agine

-1.36

 Precision

-1.35

 grav

-1.34

POSITIVE LOGITS

idon

1.57

 Mansion

1.48

ogun

1.43

 Maiden

1.42

 quarters

1.42

 Mond

1.40

Reviewer

1.39

imon

1.39

 mute

1.39

 Cathedral

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.