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

3:0.09

4:0.08

5:0.09

6:0.07

7:0.09

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

 bombard

-3.09

 bombardment

-2.65

 overfl

-2.55

 airstrike

-2.47

rahim

-2.44

 bomb

-2.41

 archae

-2.41

ql

-2.33

ansom

-2.32

akable

-2.31

POSITIVE LOGITS

 Cannabis

2.87

 Disorder

2.85

NX

2.81

 Scotia

2.74

 Benefit

2.67

 Dign

2.64

 Marijuana

2.58

 Compensation

2.56

 Beauty

2.55

 Isles

2.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.