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

1:0.08

2:0.09

3:0.08

4:0.07

5:0.09

6:0.08

7:0.08

8:0.09

9:0.07

10:0.06

11:0.08

Negative Logits

functional

-1.71

��

-1.68

 offenders

-1.63

 Haram

-1.62

soDeliveryDate

-1.61

chart

-1.53

hop

-1.52

 accountable

-1.52

program

-1.51

uploads

-1.50

POSITIVE LOGITS

aughs

1.94

urat

1.78

 Vanity

1.68

aunder

1.64

agher

1.63

orge

1.58

advertisement

1.58

eton

1.57

smanship

1.56

sonian

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.