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

0:0.09

1:0.07

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 Sailor

-2.68

 Reilly

-2.65

 cancelled

-2.62

 showc

-2.60

 delinquent

-2.49

 stranded

-2.49

 Tolkien

-2.45

 Stevenson

-2.44

 fixture

-2.42

 haunt

-2.38

POSITIVE LOGITS

 architectures

2.83

�

2.82

�

2.79

�

2.73

 praising

2.72

��

2.70

�

2.69

�

2.67

Deploy

2.62

�

2.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.