INDEX

Explanations

instances of significant events or statements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

2:0.08

3:0.07

4:0.09

5:0.08

6:0.08

7:0.08

8:0.09

9:0.07

10:0.07

11:0.08

Negative Logits

 Machines

-2.83

Lua

-2.82

DOS

-2.79

 Quake

-2.68

 Maps

-2.66

Map

-2.44

 maps

-2.44

 indexed

-2.41

TI

-2.39

 Radar

-2.38

POSITIVE LOGITS

aterasu

2.90

ishops

2.90

erest

2.86

cientious

2.83

xual

2.82

 abstinence

2.75

 charact

2.67

idav

2.65

umbledore

2.65

Cow

2.63

Activations Density 0.000%

instances of significant events or statements

No Comments

No Known Activations