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

1:0.09

2:0.08

3:0.08

4:0.07

5:0.09

6:0.08

7:0.08

8:0.07

9:0.07

10:0.08

11:0.07

Negative Logits

lied

-2.70

 Geological

-2.69

 Posts

-2.61

lay

-2.60

 Rasmussen

-2.44

 Trainer

-2.43

Media

-2.41

 Cosponsors

-2.41

 Posted

-2.38

�

-2.29

POSITIVE LOGITS

 eviction

2.89

ilogy

2.76

emo

2.73

 estates

2.69

obos

2.61

 Dickens

2.58

 forfeiture

2.58

 wines

2.56

arden

2.48

 assassins

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.