INDEX

Explanations

references to companionship or friendship

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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

Chu

-3.00

Ng

-2.70

 moon

-2.64

Pag

-2.61

 Chou

-2.59

 jung

-2.57

 Paddock

-2.56

 Saints

-2.53

pag

-2.50

 Nether

-2.49

POSITIVE LOGITS

 GOODMAN

2.83

{:

2.76

doi

2.75

istani

2.72

SPONSORED

2.61

wage

2.56

arcer

2.54

ior

2.54

ATURE

2.50

izons

2.44

Activations Density 0.000%

references to companionship or friendship

No Comments

No Known Activations