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

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.10

Negative Logits

units

-1.66

release

-1.60

Eur

-1.49

areth

-1.49

abl

-1.46

lict

-1.45

 Prism

-1.41

 Telesc

-1.40

irth

-1.39

Lys

-1.38

POSITIVE LOGITS

ikuman

1.93

 outfield

1.59

racuse

1.59

 hoops

1.59

WARE

1.56

 delinquent

1.55

Interstitial

1.54

aturdays

1.53

]]

1.53

cellaneous

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.