INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

2:0.08

3:0.08

4:0.07

5:0.09

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.06

Negative Logits

dog

-3.25

 Rafael

-2.96

MX

-2.79

 Bundesliga

-2.79

 Mate

-2.73

omore

-2.73

mate

-2.67

 Bayern

-2.66

�

-2.64

MRI

-2.64

POSITIVE LOGITS

覚醒

3.36

 reluct

3.23

 starvation

3.15

enture

3.06

 evac

2.94

 unpop

2.91

 populate

2.91

 stockp

2.90

 destruct

2.89

CRE

2.81

Activations Density 0.000%

No Known Activations

This feature has no known activations.