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

0:0.09

1:0.09

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.09

8:0.08

9:0.06

10:0.07

11:0.08

Negative Logits

pent

-2.78

control

-2.66

-2.55

COMPLE

-2.45

--------------------------------------------------------

-2.43

ヘ

-2.42

soDeliveryDate

-2.33

→

-2.28

occup

-2.24

pport

-2.23

POSITIVE LOGITS

 Emin

2.92

 Sloan

2.45

 Omar

2.36

 initials

2.27

 Elias

2.27

 microphones

2.24

 Nielsen

2.23

nikov

2.19

 Vaughn

2.19

 Bucc

2.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.