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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.09

9:0.07

10:0.08

11:0.09

Negative Logits

 Rabb

-1.83

thodox

-1.80

Sax

-1.68

��

-1.62

版

-1.58

ESE

-1.54

 longitudinal

-1.53

 circumcised

-1.52

 Agric

-1.52

ishops

-1.52

POSITIVE LOGITS

 freezes

1.82

azo

1.73

 spoil

1.67

 gravy

1.65

uru

1.64

 captcha

1.59

inia

1.56

 dictatorship

1.56

 Genie

1.55

alin

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.