INDEX

Explanations

unique identifiers or significant keywords

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

0:0.07

1:0.08

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

URA

-2.66

lus

-2.60

ilus

-2.54

]+

-2.54

 underwater

-2.53

eper

-2.48

 cables

-2.45

 vert

-2.40

orius

-2.38

 subp

-2.37

POSITIVE LOGITS

 Palin

2.86

 Planned

2.86

Zar

2.80

 Coulter

2.78

 Coinbase

2.78

manac

2.78

 Yates

2.72

 Femin

2.67

Tar

2.65

inburgh

2.63

Activations Density 0.000%

unique identifiers or significant keywords

No Comments

No Known Activations