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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.08

3:0.10

4:0.07

5:0.09

6:0.09

7:0.08

8:0.07

9:0.06

10:0.08

11:0.09

Negative Logits

android

-1.49

 BlackBerry

-1.47

iven

-1.44

aea

-1.39

science

-1.38

 newsletter

-1.36

matic

-1.35

RNA

-1.33

RNA

-1.32

rust

-1.29

POSITIVE LOGITS

adra

1.95

AKING

1.73

CONCLUS

1.69

 challeng

1.65

 Lumpur

1.65

oğ

1.64

 condem

1.64

 unaccount

1.60

 Berk

1.55

uala

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.