INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

1:0.07

2:0.07

3:0.09

4:0.08

5:0.07

6:0.08

7:0.07

8:0.10

9:0.08

10:0.09

11:0.08

Negative Logits

 days

-1.43

ATK

-1.41

 dates

-1.40

 citations

-1.39

 ticket

-1.37

 weeks

-1.37

heres

-1.34

 slots

-1.33

OTS

-1.33

taboola

-1.32

POSITIVE LOGITS

████████

1.68

 Ambro

1.67

oeuv

1.66

orget

1.65

 helicop

1.64

ebus

1.57

emale

1.57

mble

1.56

��

1.53

 pestic

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.