INDEX

Explanations

references to friendship and relationships

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.07

4:0.08

5:0.08

6:0.09

7:0.09

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

phi

-3.52

conom

-3.10

opoly

-2.90

iae

-2.87

erenn

-2.85

riers

-2.81

alon

-2.77

\/\/

-2.74

ucha

-2.72

vier

-2.72

POSITIVE LOGITS

 Anim

3.08

 Adelaide

2.94

 Shot

2.93

 Cere

2.87

 Indigenous

2.79

 Fire

2.79

 Beng

2.75

 Jakarta

2.72

 frog

2.71

 Austral

2.70

Activations Density 0.000%

references to friendship and relationships

No Comments

No Known Activations