INDEX

Explanations

capitalization of significant terms or labels

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.14

1:0.11

2:0.15

3:0.05

4:0.05

5:0.03

6:0.09

7:0.09

8:0.02

9:0.05

10:0.11

11:0.05

Negative Logits

 Hyde

-3.50

vana

-3.47

ailable

-2.96

Tob

-2.89

 heel

-2.81

Vag

-2.78

uph

-2.74

��

-2.73

 Rubber

-2.72

 Wooden

-2.67

POSITIVE LOGITS

SET

7.54

SET

6.35

 STAR

3.72

STAR

3.65

ESP

3.46

 Starfleet

3.36

 astronomer

3.31

ET

3.24

 SPEC

3.22

 Hawking

3.21

Activations Density 0.000%

capitalization of significant terms or labels

No Comments

No Known Activations