INDEX

Explanations

references to specific decades or time periods

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

0:0.08

1:0.07

2:0.09

3:0.09

4:0.07

5:0.09

6:0.08

7:0.07

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

OTAL

-3.28

Avg

-3.00

 whats

-2.87

 guiName

-2.84

Found

-2.60

ULT

-2.54

 Spaces

-2.43

 Multi

-2.43

Bus

-2.41

IF

-2.40

POSITIVE LOGITS

terness

3.23

aneers

2.99

gerald

2.89

Ruk

2.86

 Qué

2.78

龍契士

2.78

ocese

2.75

 Geral

2.75

rine

2.73

 Wynne

2.72

Activations Density 0.000%

references to specific decades or time periods

No Comments

No Known Activations