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

0:0.08

1:0.06

2:0.10

3:0.09

4:0.07

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

Increase

-1.52

\.

-1.46

iken

-1.44

�

-1.42

Capital

-1.41

 glare

-1.40

 mirrored

-1.37

 captcha

-1.37

 Plex

-1.35

flix

-1.34

POSITIVE LOGITS

odynamics

2.11

ainment

1.80

sie

1.77

 experien

1.75

gression

1.61

ividual

1.60

ainer

1.59

soDeliveryDate

1.57

adle

1.56

acebook

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.