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

1:0.05

2:0.09

3:0.08

4:0.07

5:0.09

6:0.07

7:0.07

8:0.09

9:0.09

10:0.09

11:0.08

Negative Logits

 microbi

-1.70

 Jensen

-1.63

rad

-1.45

 Targ

-1.45

 patent

-1.43

DOI

-1.41

 attRot

-1.40

 physicians

-1.39

 Band

-1.38

 Hawaiian

-1.37

POSITIVE LOGITS

olon

1.87

�

1.85

orie

1.81

�

1.75

iphate

1.72

():

1.70

CLOSE

1.69

ulhu

1.67

league

1.65

athon

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.