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

0:0.07

1:0.09

2:0.07

3:0.07

4:0.08

5:0.08

6:0.08

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

Roberts

-2.60

 unpop

-2.60

ranch

-2.53

 ballpark

-2.52

Cub

-2.47

Krist

-2.44

ritic

-2.44

 depl

-2.37

conserv

-2.35

 reluct

-2.34

POSITIVE LOGITS

 Leilan

2.90

 Kinnikuman

2.89

 Bulldogs

2.84

 Valkyrie

2.79

 Rune

2.79

 Psycho

2.78

 Hume

2.75

 Highlander

2.75

 Torch

2.61

morrow

2.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.