INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

orry

-2.79

thora

-2.66

risome

-2.66

osate

-2.59

 Charter

-2.57

rase

-2.55

arming

-2.54

otide

-2.52

roach

-2.46

rolet

-2.44

POSITIVE LOGITS

 withd

2.91

 skelet

2.74

yg

2.72

 toget

2.63

ultane

2.63

 circumcised

2.55

Doc

2.55

 resemb

2.43

ANG

2.39

ABC

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.