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

0:0.08

1:0.09

2:0.07

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 Coch

-3.16

 Mood

-2.97

 Aging

-2.86

 Treatment

-2.82

 Therapy

-2.47

 Clinical

-2.46

 Topics

-2.42

Hab

-2.42

rium

-2.40

 Applied

-2.40

POSITIVE LOGITS

GUN

2.86

ulhu

2.71

adoes

2.69

selage

2.66

rawdownloadcloneembedreportprint

2.60

utral

2.59

 undo

2.58

ANE

2.56

▬

2.56

 lantern

2.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.