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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.07

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

psy

-1.82

 Nadu

-1.81

Wyr

-1.68

rences

-1.68

enges

-1.66

veyard

-1.64

viron

-1.61

 Immunity

-1.57

ances

-1.49

 Gerr

-1.46

POSITIVE LOGITS

 encrypt

1.54

ington

1.48

 disclaim

1.47

 interns

1.47

 pian

1.44

 widgets

1.43

 encryption

1.43

erto

1.43

 shooters

1.42

Reviewer

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.