INDEX

Explanations

specific names associated with locations or organizations

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

2:0.07

3:0.09

4:0.06

5:0.09

6:0.08

7:0.09

8:0.07

9:0.08

10:0.07

11:0.07

Negative Logits

 Mech

-2.62

 Boost

-2.53

thy

-2.51

 Lilith

-2.51

 Brush

-2.45

Ner

-2.41

Bot

-2.39

�

-2.37

 Fool

-2.30

workshop

-2.30

POSITIVE LOGITS

asio

2.71

 looted

2.63

 theat

2.62

Ari

2.54

 disembark

2.51

 dispersed

2.50

 surrog

2.50

Cas

2.47

���

2.45

 surrogate

2.44

Activations Density 0.000%

specific names associated with locations or organizations

No Comments

No Known Activations