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

0:0.07

1:0.06

2:0.09

3:0.10

4:0.09

5:0.08

6:0.07

7:0.08

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

 incomplete

-1.54

skip

-1.46

�士

-1.42

 complete

-1.40

 unequ

-1.40

 Highlander

-1.38

 prec

-1.36

 Bung

-1.35

 nutshell

-1.33

 spoiler

-1.33

POSITIVE LOGITS

emet

1.82

NetMessage

1.81

iferation

1.69

ysical

1.58

 challeng

1.57

irms

1.57

arters

1.53

pora

1.48

ardi

1.46

rower

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.