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

0:0.08

1:0.07

2:0.10

3:0.08

4:0.07

5:0.07

6:0.07

7:0.08

8:0.08

9:0.07

10:0.10

11:0.07

Negative Logits

hur

-1.60

taboola

-1.51

oop

-1.50

laugh

-1.46

livious

-1.45

reek

-1.43

[*

-1.43

Dek

-1.43

 Centauri

-1.41

 Buff

-1.40

POSITIVE LOGITS

の魔

1.79

thood

1.72

isites

1.57

 manufact

1.51

iversary

1.50

ocrates

1.50

ciation

1.48

 manifesto

1.47

 achieved

1.42

の�

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.