INDEX

Explanations

references to political affiliations and group dynamics

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.01

1:0.02

2:0.09

3:0.11

4:0.29

5:0.02

6:0.08

7:0.14

8:0.02

9:0.02

10:0.07

11:0.08

Negative Logits

inventoryQuantity

-1.68

 originated

-1.57

Columb

-1.55

ciation

-1.53

 orig

-1.51

 Transformation

-1.50

agne

-1.50

 Procedures

-1.49

 existed

-1.44

OVA

-1.43

POSITIVE LOGITS

ographers

2.05

 passers

1.99

 onlook

1.91

untled

1.90

 insiders

1.85

 backers

1.81

 experts

1.81

 analysts

1.79

 filmmakers

1.75

 growers

1.74

Activations Density 0.076%

references to political affiliations and group dynamics

No Comments

No Known Activations