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

1:0.08

2:0.07

3:0.08

4:0.08

5:0.09

6:0.09

7:0.09

8:0.07

9:0.07

10:0.09

11:0.07

Negative Logits

tha

-1.60

mers

-1.60

 Magicka

-1.59

 Gamma

-1.57

 Psychiat

-1.57

MQ

-1.57

timer

-1.51

kus

-1.49

ammers

-1.48

nil

-1.46

POSITIVE LOGITS

 bonding

1.69

 sparing

1.69

 pestic

1.60

 evenly

1.52

sole

1.51

 FANT

1.50

actively

1.50

 bonds

1.49

assad

1.46

 ordinance

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.