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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.08

4:0.09

5:0.07

6:0.08

7:0.08

8:0.09

9:0.09

10:0.08

11:0.07

Negative Logits

 locality

-3.02

 neighbourhoods

-2.60

 contextual

-2.58

 neighbourhood

-2.57

 favoured

-2.56

 anthology

-2.55

fav

-2.50

 favour

-2.46

 anch

-2.45

 marginal

-2.43

POSITIVE LOGITS

ioxide

2.93

oops

2.86

iron

2.73

Boo

2.62

 Shooting

2.50

 Employees

2.50

 Experts

2.48

apo

2.48

 Shoot

2.44

rike

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.