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

0:0.08

1:0.07

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

Beg

-1.91

Gil

-1.46

PLA

-1.46

��

-1.42

��

-1.41

hello

-1.41

script

-1.38

Albert

-1.37

Jerry

-1.36

 Stev

-1.35

POSITIVE LOGITS

 mutants

1.75

 tentacles

1.68

zag

1.54

 Disorders

1.52

 oats

1.51

 Refugees

1.51

ngth

1.50

afety

1.48

 salads

1.47

ieri

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.