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

3:0.08

4:0.08

5:0.08

6:0.09

7:0.08

8:0.07

9:0.08

10:0.09

11:0.07

Negative Logits

 Usage

-2.90

SpaceEngineers

-2.79

taboola

-2.69

geant

-2.67

 Assignment

-2.58

 assignments

-2.56

 Salary

-2.56

 Output

-2.52

specified

-2.47

 Typical

-2.44

POSITIVE LOGITS

 judiciary

2.60

 monuments

2.56

 runes

2.54

 rebuilt

2.50

nah

2.49

 innocence

2.49

 Azerbaijan

2.44

 ivory

2.44

 elephants

2.41

 Ashe

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.