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

2:0.09

3:0.07

4:0.09

5:0.08

6:0.09

7:0.07

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

 Scores

-1.74

Downloadha

-1.72

 spir

-1.63

erity

-1.58

pleting

-1.54

outed

-1.51

 Opportunity

-1.51

 surged

-1.50

 fielded

-1.50

assium

-1.49

POSITIVE LOGITS

Spoiler

1.70

ALE

1.67

 Centauri

1.58

ZA

1.56

Cub

1.54

Privacy

1.54

 astronaut

1.54

Rob

1.54

CW

1.52

 deaf

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.