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

1:0.08

2:0.10

3:0.09

4:0.07

5:0.07

6:0.07

7:0.08

8:0.07

9:0.07

10:0.08

11:0.07

Negative Logits

natureconservancy

-2.69

 Skinner

-2.62

ayne

-2.52

Tang

-2.49

Minnesota

-2.46

Tu

-2.45

danger

-2.44

resistant

-2.41

Saharan

-2.36

omsday

-2.35

POSITIVE LOGITS

Zot

2.83

 Fifa

2.64

 Atom

2.49

chery

2.45

 Babe

2.42

2.36

 appe

2.36

 Archive

2.35

2.33

2.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.