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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.09

3:0.09

4:0.08

5:0.07

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

龍�

-3.31

Tud

-3.23

 Kingston

-3.06

Jenn

-3.04

inka

-2.92

 Trin

-2.74

 Joyce

-2.63

enty

-2.63

女

-2.63

odox

-2.61

POSITIVE LOGITS

 Cooldown

2.68

 seizure

2.46

 labeled

2.38

 mouths

2.36

 recognize

2.35

 Adren

2.34

ALE

2.31

FIG

2.26

 seizures

2.26

 abstract

2.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.