INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

2:0.07

3:0.08

4:0.10

5:0.08

6:0.08

7:0.07

8:0.07

9:0.07

10:0.09

11:0.09

Negative Logits

 squats

-3.67

 clitor

-3.00

galitarian

-2.95

 Brun

-2.82

 Kraft

-2.78

MRI

-2.74

 masse

-2.72

 Luxembourg

-2.71

 Mart

-2.64

enz

-2.63

POSITIVE LOGITS

####

2.89

aii

2.66

################################

2.61

REAM

2.58

 DACA

2.58

ALD

2.56

 ACTIONS

2.54

�

2.53

###

2.53

intent

2.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.