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

0:0.09

1:0.07

2:0.09

3:0.07

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 mill

-1.63

 Mill

-1.63

Alz

-1.58

Zy

-1.58

 Burr

-1.57

 Reincarn

-1.55

 Phar

-1.48

 gest

-1.47

 Primal

-1.43

Hex

-1.43

POSITIVE LOGITS

urally

2.04

Spoiler

1.98

ategories

1.81

★★

1.75

CEPT

1.74

ussie

1.74

..............

1.74

notations

1.72

requisite

1.70

eatures

1.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.