INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

1:0.07

2:0.07

3:0.08

4:0.09

5:0.07

6:0.09

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 Supporters

-2.74

Oy

-2.49

 Mosque

-2.45

 Irma

-2.21

 Warriors

-2.21

 Earthqu

-2.20

Raf

-2.19

 Revenue

-2.18

Mi

-2.15

 Toll

-2.13

POSITIVE LOGITS

 carbohyd

2.79

ittle

2.45

quickShipAvailable

2.39

ixie

2.33

pees

2.25

livious

2.24

覚醒

2.23

DN

2.22

acement

2.22

aution

2.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.