INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

2:0.07

3:0.08

4:0.09

5:0.08

6:0.10

7:0.09

8:0.07

9:0.06

10:0.07

11:0.08

Negative Logits

chu

-1.58

 Trigger

-1.49

rahim

-1.46

 Scarlet

-1.43

thy

-1.41

dan

-1.35

ilda

-1.33

ppa

-1.31

 Rober

-1.30

asta

-1.29

POSITIVE LOGITS

igslist

2.02

Newsletter

1.62

 substitutes

1.50

 ministries

1.48

uggest

1.48

 reperto

1.46

 arrang

1.45

 nurs

1.43

 OPEC

1.42

 subdiv

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.