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

1:0.05

2:0.10

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

 QUEST

-1.53

 playthrough

-1.48

 secondly

-1.48

\/\/

-1.46

-1.45

 empath

-1.44

 Analog

-1.42

 Originally

-1.41

 unavoid

-1.40

 Suff

-1.39

POSITIVE LOGITS

inance

1.65

�醒

1.64

mble

1.63

senal

1.62

dal

1.56

umbn

1.54

 gard

1.46

gian

1.45

raq

1.44

mg

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.