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

1:0.09

2:0.08

3:0.08

4:0.07

5:0.08

6:0.08

7:0.07

8:0.08

9:0.09

10:0.08

11:0.07

Negative Logits

 Saur

-2.75

 charism

-2.62

Gad

-2.55

 Sabha

-2.52

dod

-2.45

 Gadget

-2.42

Kab

-2.40

 Slater

-2.40

 Davies

-2.31

 Skydragon

-2.31

POSITIVE LOGITS

2.55

2.41

renheit

2.37

 anesthesia

2.34

�

2.21

imore

2.21

trigger

2.21

 gravity

2.21

 morale

2.19

Activations Density 0.000%

No Known Activations

This feature has no known activations.