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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

NetMessage

-1.75

htaking

-1.59

bod

-1.51

selage

-1.48

 describ

-1.48

 surpr

-1.47

acter

-1.47

ocene

-1.46

 looph

-1.44

 rover

-1.44

POSITIVE LOGITS

nuts

1.68

azines

1.60

RTX

1.48

mx

1.46

ubi

1.44

parts

1.44

stores

1.43

vation

1.41

 Shares

1.41

ews

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.